The Option-Critic Architecture
|
|
- Timothy Atkins
- 6 years ago
- Views:
Transcription
1 The Option-Critic Architecture Pierre-Luc Bacon, Jean Harb, Doina Precup Reasoning and Learning Lab McGill University, Montreal, Canada AAAI 2017
2 Intelligence: the ability to generalize and adapt efficiently to new and uncertain situations Having good representations is key [...] solving a problem simply means representing it so as to make the solution transparent. Simon, / 18
3 Reinforcement Learning: a general framework for AI Equipped with a good state representation, RL has led to impressive results: Tesauro s TD Gammon (1995), Watson s Daily-Double Wagering in Jeopardy! (2013), Human-level video game play in the Atari games (2013), AlphaGo (2016)... The ability to abstract knowledge temporally over many different time scales is still missing. 2 / 18
4 Temporal abstraction Higher level steps Choosing the type of coffee maker, type of coffee beans Medium level steps Grind the beans, measure the right quantity of water, boil the water Lower level steps Wrist and arm movements while adding coffee to the filter,... 3 / 18
5 Temporal abstraction in AI A cornerstone of AI planning since the 1970 s: Fikes et al. (1972), Newell (1972, Kuipers (1979), Korf (1985), Laird (1986), Iba (1989), Drescher (1991) etc. It has been shown to : Generate shorter plans Reduce the complexity of choosing actions Provide robustness against model misspecification Improve exploration by taking shortcuts in the environment 4 / 18
6 Temporal abstraction in RL Options (Sutton, Singh, Precup 2000) can represent courses of action at variable time scales: High level Low level Trajectory, time 5 / 18
7 Options framework An option ω is a triple: 1. initiation set: I ω 2. internal policy: π ω 3. termination condition: β ω Example Robot navigation: if there is no obstacle in front (I ω ), go forward (π ω ) until you get too close to another object (β ω ) We can derive a policy over options π Ω that maximizes the expected discounted sum of rewards: [ ] E γ t r(s t, a t ) s 0, ω 0 t=0 6 / 18
8 Contribution of this work The problem of constructing/discovering good options has been a challenge for more than 15 years. Option-critic is a scalable solution to this problem: Online, continual and model-free (but models can be used if desired) Requires no a priori domain knowledge, decomposition, or human intervention Learns in a single task, at least as fast as other methods which do not use temporal abstraction Applies to general continuous state and action spaces 7 / 18
9 Actor-Critic Architecture (Sutton 1984) Actor Policy Gradient s t Critic Value function TD error a t r t Environment The policy (actor) is decoupled from its value function. The critic provides feedback to improve the actor Learning is fully online 8 / 18
10 Option-Critic Architecture Policy over options π Ω ω t Options π ω, β ω Gradients s t Critic Q U, A Ω TD error a t r t Environment Parameterize internal policies and termination conditions Policy over options is computed by a separate process 9 / 18
11 Main result: Gradient updates The gradient wrt. the internal policy parameters θ is given by: [ ] log πω,θ (a s) E Q U (s, ω, a) θ This has the usual interpretation: take better primitives more often inside the option The gradient wrt. the termination parameters ν is given by: [ E β ω,ν(s ] ) A πω (s, ω) ν where A πω = Q πω V πω is the advantage function This means that we want to lengthen options that have a large advantage 10 / 18
12 Results: Options transfer Hallways Walls Initial goal Random goal after 1000 episodes 11 / 18
13 Results: Options transfer Goal moves randomly SARSA(0) AC-PG OC 4 options OC 8 options Steps Episodes Primitive actions Using temporal abstractions discovered by option-critic Learning in the first task no slower than using primitives Learning once the goal is moved faster with the options 12 / 18
14 Results: Learned options are intuitive Probability of terminating in a particular state, for each option: Option 1 Option 2 Option 3 Option 4 Terminations are more likely near hallways (although there are no pseudo-rewards provided) 13 / 18
15 Results: Nonlinear function approximation Policy over options Termination functions Internal policies Last 4 frames Convolutional layers Shared representation Same architecture as DQN (Mnih & al., 2013) for the 4 first layers but hybridized with options and the policy over them. 14 / 18
16 Performance matching or better than DQN Avg. Score Option-Critic 500 Option-Critic 0 DQN DQN Epoch Epoch (a) Asterix (b) Ms. Pacman Option-Critic DQN Option-Critic DQN Epoch Epoch (c) Seaquest (d) Zaxxon 15 / 18
17 Interpretable and specialized options in Seaquest Action trajectory, time White: option 1 Black: option 2 Transition from option 1 to 2 Option 1: downward shooting sequences Option 2: upward shooting sequences 16 / 18
18 Conclusion Our results seem to be the first to be: fully end-to-end within a single task at speed comparable or better than using just primitive methods Using ideas from policy gradient methods, option-critic provides continual option construction can be used with nonlinear function approximators can incorporate regularizers or pseudo-rewards easily 17 / 18
19 Future work Learn initiation sets: Would require a new notion of stochastic initiation functions More empirical results! Try our code : 18 / 18
How to construct good temporal abstractions. Doina Precup McGill University Joint work with Pierre-Luc Bacon and Jean Mehreb-Harb
How to construct good temporal abstractions Doina Precup McGill University Joint work with Pierre-Luc Bacon and Jean Mehreb-Harb EWRL, December 2016 Options framework Suppose we have an MDP S, A, r, P,
More informationThe Problem of Temporal Abstraction
The Problem of Temporal Abstraction How do we connect the high level to the low-level? " the human level to the physical level? " the decide level to the action level? MDPs are great, search is great,
More informationReinforcement Learning. Slides based on those used in Berkeley's AI class taught by Dan Klein
Reinforcement Learning Slides based on those used in Berkeley's AI class taught by Dan Klein Reinforcement Learning Basic idea: Receive feedback in the form of rewards Agent s utility is defined by the
More informationTemporal Abstraction in RL
Temporal Abstraction in RL How can an agent represent stochastic, closed-loop, temporally-extended courses of action? How can it act, learn, and plan using such representations? HAMs (Parr & Russell 1998;
More information4 Reinforcement Learning Basic Algorithms
Learning in Complex Systems Spring 2011 Lecture Notes Nahum Shimkin 4 Reinforcement Learning Basic Algorithms 4.1 Introduction RL methods essentially deal with the solution of (optimal) control problems
More informationIntroduction to Reinforcement Learning. MAL Seminar
Introduction to Reinforcement Learning MAL Seminar 2014-2015 RL Background Learning by interacting with the environment Reward good behavior, punish bad behavior Trial & Error Combines ideas from psychology
More informationReinforcement Learning
Reinforcement Learning Basic idea: Receive feedback in the form of rewards Agent s utility is defined by the reward function Must (learn to) act so as to maximize expected rewards Grid World The agent
More informationReinforcement Learning
Reinforcement Learning Hierarchical Reinforcement Learning Action hierarchy, hierarchical RL, semi-mdp Vien Ngo Marc Toussaint University of Stuttgart Outline Hierarchical reinforcement learning Learning
More informationReinforcement Learning. Monte Carlo and Temporal Difference Learning
Reinforcement Learning Monte Carlo and Temporal Difference Learning Manfred Huber 2014 1 Monte Carlo Methods Dynamic Programming Requires complete knowledge of the MDP Spends equal time on each part of
More informationCSE 473: Artificial Intelligence
CSE 473: Artificial Intelligence Markov Decision Processes (MDPs) Luke Zettlemoyer Many slides over the course adapted from Dan Klein, Stuart Russell or Andrew Moore 1 Announcements PS2 online now Due
More informationTemporal Abstraction in RL. Outline. Example. Markov Decision Processes (MDPs) ! Options
Temporal Abstraction in RL Outline How can an agent represent stochastic, closed-loop, temporally-extended courses of action? How can it act, learn, and plan using such representations?! HAMs (Parr & Russell
More informationDeep Learning and Reinforcement Learning
Deep Learning and Reinforcement Learning Razvan Pascanu (Google DeepMind) Razvan Pascanu (Google DeepMind) Deep Learning and Reinforcement Learning 17 August 2015 1/ 40 Disclaimers: Slides based on David
More informationCS 461: Machine Learning Lecture 8
CS 461: Machine Learning Lecture 8 Dr. Kiri Wagstaff kiri.wagstaff@calstatela.edu 2/23/08 CS 461, Winter 2008 1 Plan for Today Review Clustering Reinforcement Learning How different from supervised, unsupervised?
More informationCSEP 573: Artificial Intelligence
CSEP 573: Artificial Intelligence Markov Decision Processes (MDP)! Ali Farhadi Many slides over the course adapted from Luke Zettlemoyer, Dan Klein, Pieter Abbeel, Stuart Russell or Andrew Moore 1 Outline
More informationCOMP417 Introduction to Robotics and Intelligent Systems. Reinforcement Learning - 2
COMP417 Introduction to Robotics and Intelligent Systems Reinforcement Learning - 2 Speaker: Sandeep Manjanna Acklowledgement: These slides use material from Pieter Abbeel s, Dan Klein s and John Schulman
More informationReinforcement Learning
Reinforcement Learning MDP March May, 2013 MDP MDP: S, A, P, R, γ, µ State can be partially observable: Partially Observable MDPs () Actions can be temporally extended: Semi MDPs (SMDPs) and Hierarchical
More information2D5362 Machine Learning
2D5362 Machine Learning Reinforcement Learning MIT GALib Available at http://lancet.mit.edu/ga/ download galib245.tar.gz gunzip galib245.tar.gz tar xvf galib245.tar cd galib245 make or access my files
More informationLecture 17: More on Markov Decision Processes. Reinforcement learning
Lecture 17: More on Markov Decision Processes. Reinforcement learning Learning a model: maximum likelihood Learning a value function directly Monte Carlo Temporal-difference (TD) learning COMP-424, Lecture
More informationEnsemble Methods for Reinforcement Learning with Function Approximation
Ensemble Methods for Reinforcement Learning with Function Approximation Stefan Faußer and Friedhelm Schwenker Institute of Neural Information Processing, University of Ulm, 89069 Ulm, Germany {stefan.fausser,friedhelm.schwenker}@uni-ulm.de
More informationLecture 12: MDP1. Victor R. Lesser. CMPSCI 683 Fall 2010
Lecture 12: MDP1 Victor R. Lesser CMPSCI 683 Fall 2010 Biased Random GSAT - WalkSat Notice no random restart 2 Today s lecture Search where there is Uncertainty in Operator Outcome --Sequential Decision
More informationCS221 / Spring 2018 / Sadigh. Lecture 8: MDPs II
CS221 / Spring 218 / Sadigh Lecture 8: MDPs II cs221.stanford.edu/q Question If you wanted to go from Orbisonia to Rockhill, how would you get there? ride bus 1 ride bus 17 ride the magic tram CS221 /
More informationCS 360: Advanced Artificial Intelligence Class #16: Reinforcement Learning
CS 360: Advanced Artificial Intelligence Class #16: Reinforcement Learning Daniel M. Gaines Note: content for slides adapted from Sutton and Barto [1998] Introduction Animals learn through interaction
More informationReinforcement learning and Markov Decision Processes (MDPs) (B) Avrim Blum
Reinforcement learning and Markov Decision Processes (MDPs) 15-859(B) Avrim Blum RL and MDPs General scenario: We are an agent in some state. Have observations, perform actions, get rewards. (See lights,
More informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2011 Lecture 9: MDPs 2/16/2011 Pieter Abbeel UC Berkeley Many slides over the course adapted from either Dan Klein, Stuart Russell or Andrew Moore 1 Announcements
More informationCS 188: Artificial Intelligence
CS 188: Artificial Intelligence Markov Decision Processes Dan Klein, Pieter Abbeel University of California, Berkeley Non Deterministic Search Example: Grid World A maze like problem The agent lives in
More informationCS221 / Autumn 2018 / Liang. Lecture 8: MDPs II
CS221 / Autumn 218 / Liang Lecture 8: MDPs II cs221.stanford.edu/q Question If you wanted to go from Orbisonia to Rockhill, how would you get there? ride bus 1 ride bus 17 ride the magic tram CS221 / Autumn
More informationImportance Sampling for Fair Policy Selection
Importance Sampling for Fair Policy Selection Shayan Doroudi Carnegie Mellon University Pittsburgh, PA 15213 shayand@cs.cmu.edu Philip S. Thomas Carnegie Mellon University Pittsburgh, PA 15213 philipt@cs.cmu.edu
More information91.420/543: Artificial Intelligence UMass Lowell CS Fall 2010
91.420/543: Artificial Intelligence UMass Lowell CS Fall 2010 Lecture 17 & 18: Markov Decision Processes Oct 12 13, 2010 A subset of Lecture 9 slides from Dan Klein UC Berkeley Many slides over the course
More informationReinforcement Learning 04 - Monte Carlo. Elena, Xi
Reinforcement Learning 04 - Monte Carlo Elena, Xi Previous lecture 2 Markov Decision Processes Markov decision processes formally describe an environment for reinforcement learning where the environment
More informationMotivation: disadvantages of MC methods MC does not work for scenarios without termination It updates only at the end of the episode (sometimes - it i
Temporal-Di erence Learning Taras Kucherenko, Joonatan Manttari KTH tarask@kth.se manttari@kth.se March 7, 2017 Taras Kucherenko, Joonatan Manttari (KTH) TD-Learning March 7, 2017 1 / 68 Motivation: disadvantages
More informationIntra-Option Learning about Temporally Abstract Actions
Intra-Option Learning about Temporally Abstract Actions Richard S. Sutton Department of Computer Science University of Massachusetts Amherst, MA 01003-4610 rich@cs.umass.edu Doina Precup Department of
More informationCS 188: Artificial Intelligence
CS 188: Artificial Intelligence Markov Decision Processes Dan Klein, Pieter Abbeel University of California, Berkeley Non-Deterministic Search 1 Example: Grid World A maze-like problem The agent lives
More informationBetween MDPs and Semi-MDPs: Learning, Planning, and Representing Knowledge at Multiple Temporal Scales
Journal of Artificial Intelligence Research 1 (1998) 1-39 Submitted 3/98; published NOT Between MDPs and Semi-MDPs: Learning, Planning, and Representing Knowledge at Multiple Temporal Scales Richard S.
More informationTrade and Manage Wealth with Deep RL and Memory
Trade and Manage Wealth with Deep RL and Memory NVIDIA GTC 2018 March 26, 2018 Daniel Egloff, Founder, CEO, Head R&D Problem Retail investor customer demands Manage portfolio more actively Get additional
More informationReinforcement Learning and Simulation-Based Search
Reinforcement Learning and Simulation-Based Search David Silver Outline 1 Reinforcement Learning 2 3 Planning Under Uncertainty Reinforcement Learning Markov Decision Process Definition A Markov Decision
More informationInverse reinforcement learning from summary data
Inverse reinforcement learning from summary data Antti Kangasrääsiö, Samuel Kaski Aalto University, Finland ECML PKDD 2018 journal track Published in Machine Learning (2018), 107:1517 1535 September 12,
More informationStrategy Acquisition for the Game Othello Based on Reinforcement Learning
Strategy Acquisition for the Game Othello Based on Reinforcement Learning Taku Yoshioka, Shin Ishii and Minoru Ito IEICE Transactions on Information and System 1999 Speaker : Sameer Agarwal Course : Learning
More informationMonte Carlo Methods (Estimators, On-policy/Off-policy Learning)
1 / 24 Monte Carlo Methods (Estimators, On-policy/Off-policy Learning) Julie Nutini MLRG - Winter Term 2 January 24 th, 2017 2 / 24 Monte Carlo Methods Monte Carlo (MC) methods are learning methods, used
More informationCS 188 Fall Introduction to Artificial Intelligence Midterm 1. ˆ You have approximately 2 hours and 50 minutes.
CS 188 Fall 2013 Introduction to Artificial Intelligence Midterm 1 ˆ You have approximately 2 hours and 50 minutes. ˆ The exam is closed book, closed notes except your one-page crib sheet. ˆ Please use
More informationReinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration
Reinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration Piyush Rai CS5350/6350: Machine Learning November 29, 2011 Reinforcement Learning Supervised Learning: Uses explicit supervision
More informationCompositional Planning Using Optimal Option Models
David Silver d.silver@cs.ucl.ac.uk Kamil Ciosek k.ciosek@cs.ucl.ac.uk Department of Computer Science, CSML, University College London, Gower Street, London WC1E 6BT. Abstract In this paper we introduce
More informationSequential Decision Making
Sequential Decision Making Dynamic programming Christos Dimitrakakis Intelligent Autonomous Systems, IvI, University of Amsterdam, The Netherlands March 18, 2008 Introduction Some examples Dynamic programming
More informationReinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration
Reinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration Piyush Rai CS5350/6350: Machine Learning November 29, 2011 Reinforcement Learning Supervised Learning: Uses explicit supervision
More informationIterative Hierarchical Optimization for Misspecified Problems
Iterative Hierarchical Optimization for Misspecified Problems Daniel J. Mankowitz 1 Timothy A. Mann 2 Shie Mannor 1 danielm@tx.technion.ac.il timothymann@google.com shie@@ee.technion.ac.il Abstract For
More informationCS221 / Spring 2018 / Sadigh. Lecture 9: Games I
CS221 / Spring 2018 / Sadigh Lecture 9: Games I Course plan Search problems Markov decision processes Adversarial games Constraint satisfaction problems Bayesian networks Reflex States Variables Logic
More informationLearning in a Small World
Learning in a Small World Arun Tejasvi Chaganty Deptt. of Computer Science and Engineering, IIT Madras Chennai, India - 600036 arunc@cse.iitm.ac.in Prateek Gaur Deptt. of Computer Science and Engineering,
More informationLecture 9: Games I. Course plan. A simple game. Roadmap. Machine learning. Example: game 1
Lecture 9: Games I Course plan Search problems Markov decision processes Adversarial games Constraint satisfaction problems Bayesian networks Reflex States Variables Logic Low-level intelligence Machine
More information10703 Deep Reinforcement Learning and Control
10703 Deep Reinforcement Learning and Control Russ Salakhutdinov Machine Learning Department rsalakhu@cs.cmu.edu Temporal Difference Learning Used Materials Disclaimer: Much of the material and slides
More informationarxiv: v1 [cs.lg] 19 Nov 2018
Practical Deep Reinforcement Learning Approach for Stock Trading arxiv:1811.07522v1 [cs.lg] 19 Nov 2018 Zhuoran Xiong, Xiao-Yang Liu, Shan Zhong, Hongyang (Bruce) Yang +, and Anwar Walid Electrical Engineering,
More informationReinforcement Learning Lectures 4 and 5
Reinforcement Learning Lectures 4 and 5 Gillian Hayes 18th January 2007 Reinforcement Learning 1 Framework Rewards, Returns Environment Dynamics Components of a Problem Values and Action Values, V and
More informationComparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return
Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return Craig Sherstan 1, Dylan R. Ashley 2, Brendan Bennett 2, Kenny Young, Adam White, Martha White, Richard
More informationDecision making in the presence of uncertainty
CS 2750 Foundations of AI Lecture 20 Decision making in the presence of uncertainty Milos Hauskrecht milos@cs.pitt.edu 5329 Sennott Square Decision-making in the presence of uncertainty Computing the probability
More informationTDT4171 Artificial Intelligence Methods
TDT47 Artificial Intelligence Methods Lecture 7 Making Complex Decisions Norwegian University of Science and Technology Helge Langseth IT-VEST 0 helgel@idi.ntnu.no TDT47 Artificial Intelligence Methods
More informationCS 6300 Artificial Intelligence Spring 2018
Expectimax Search CS 6300 Artificial Intelligence Spring 2018 Tucker Hermans thermans@cs.utah.edu Many slides courtesy of Pieter Abbeel and Dan Klein Expectimax Search Trees What if we don t know what
More informationDynamic Programming and Reinforcement Learning
Dynamic Programming and Reinforcement Learning Daniel Russo Columbia Business School Decision Risk and Operations Division Fall, 2017 Daniel Russo (Columbia) Fall 2017 1 / 34 Supervised Machine Learning
More informationMarkov Decision Processes
Markov Decision Processes Robert Platt Northeastern University Some images and slides are used from: 1. CS188 UC Berkeley 2. AIMA 3. Chris Amato Stochastic domains So far, we have studied search Can use
More informationReinforcement Learning
Reinforcement Learning Monte Carlo Methods Heiko Zimmermann 15.05.2017 1 Monte Carlo Monte Carlo policy evaluation First visit policy evaluation Estimating q values On policy methods Off policy methods
More informationBetween MDPs and semi-mdps: A framework for temporal abstraction in reinforcement learning
Artificial Intelligence 112 (1999) 181 211 Between MDPs and semi-mdps: A framework for temporal abstraction in reinforcement learning Richard S. Sutton a,, Doina Precup b, Satinder Singh a a AT&T Labs.-Research,
More informationLogistics. CS 473: Artificial Intelligence. Markov Decision Processes. PS 2 due today Midterm in one week
CS 473: Artificial Intelligence Markov Decision Processes Dan Weld University of Washington [Slides originally created by Dan Klein & Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All CS188 materials
More informationReinforcement Learning
Reinforcement Learning Model-based RL and Integrated Learning-Planning Planning and Search, Model Learning, Dyna Architecture, Exploration-Exploitation (many slides from lectures of Marc Toussaint & David
More informationNon-Deterministic Search
Non-Deterministic Search MDP s 1 Non-Deterministic Search How do you plan (search) when your actions might fail? In general case, how do you plan, when the actions have multiple possible outcomes? 2 Example:
More informationA Short Survey on Pursuit-Evasion Games
A Short Survey on Pursuit-Evasion Games Peng Cheng Dept. of Computer Science University of Illinois at Urbana-Champaign 1 Introduction Pursuit-evasion game is about how to guide one or a group of pursuers
More informationReasoning with Uncertainty
Reasoning with Uncertainty Markov Decision Models Manfred Huber 2015 1 Markov Decision Process Models Markov models represent the behavior of a random process, including its internal state and the externally
More informationc 2004 IEEE. Reprinted from the Proceedings of the International Joint Conference on Neural Networks (IJCNN-2004), Budapest, Hungary, pp
c 24 IEEE. Reprinted from the Proceedings of the International Joint Conference on Neural Networks (IJCNN-24), Budapest, Hungary, pp. 197 112. This material is posted here with permission of the IEEE.
More informationReinforcement Learning. n-armed bandit. n-armed bandit. n-armed bandit estimate. Kevin Spiteri April 21, 2015
Reinforement Learning n-armed andit Kevin Spiteri April 21, 2015 n-armed andit n-armed andit 0.9 0.5 0.1 0.9 0.5 0.1 0.0 0.0 0.0 estimate n-armed andit n-armed andit 0.9 0.5 0.1 0.9 0.5 0.1 0 0.0 0.0 0.0
More informationSequential Coalition Formation for Uncertain Environments
Sequential Coalition Formation for Uncertain Environments Hosam Hanna Computer Sciences Department GREYC - University of Caen 14032 Caen - France hanna@info.unicaen.fr Abstract In several applications,
More informationBudget Management In GSP (2018)
Budget Management In GSP (2018) Yahoo! March 18, 2018 Miguel March 18, 2018 1 / 26 Today s Presentation: Budget Management Strategies in Repeated auctions, Balseiro, Kim, and Mahdian, WWW2017 Learning
More informationReinforcement Learning
Reinforcement Learning n-step bootstrapping Daniel Hennes 12.06.2017 University Stuttgart - IPVS - Machine Learning & Robotics 1 n-step bootstrapping Unifying Monte Carlo and TD n-step TD n-step Sarsa
More informationAn Academic View on the Illiquidity Premium and Market-Consistent Valuation in Insurance
An Academic View on the Illiquidity Premium and Market-Consistent Valuation in Insurance Mario V. Wüthrich April 15, 2011 Abstract The insurance industry currently discusses to which extent they can integrate
More informationTo earn the extra credit, one of the following has to hold true. Please circle and sign.
CS 188 Fall 2018 Introduction to Artificial Intelligence Practice Midterm 1 To earn the extra credit, one of the following has to hold true. Please circle and sign. A I spent 2 or more hours on the practice
More informationDesigning a Hybrid AI System as a Forex Trading Decision Support Tool
Designing a Hybrid AI System as a Forex Trading Decision Support Tool Lean Yu Kin Keung Lai Shouyang Wang Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, 00080, China
More informationMDPs: Bellman Equations, Value Iteration
MDPs: Bellman Equations, Value Iteration Sutton & Barto Ch 4 (Cf. AIMA Ch 17, Section 2-3) Adapted from slides kindly shared by Stuart Russell Sutton & Barto Ch 4 (Cf. AIMA Ch 17, Section 2-3) 1 Appreciations
More informationMean Reverting Asset Trading. Research Topic Presentation CSCI-5551 Grant Meyers
Mean Reverting Asset Trading Research Topic Presentation CSCI-5551 Grant Meyers Table of Contents 1. Introduction + Associated Information 2. Problem Definition 3. Possible Solution 1 4. Problems with
More informationLearning to Trade with Insider Information
Learning to Trade with Insider Information Sanmay Das Center for Biological and Computational Learning and Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology
More informationUsing Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation
Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation Zhaohan Daniel Guo Carnegie Mellon University Pittsburgh, PA 15213 zguo@cs.cmu.edu Philip S. Thomas University of Massachusetts
More informationarxiv: v2 [cs.lg] 2 Dec 2018
Practical Deep Reinforcement Learning Approach for Stock Trading arxiv:1811.07522v2 [cs.lg] 2 Dec 2018 Zhuoran Xiong, Xiao-Yang Liu, Shan Zhong, Hongyang (Bruce) Yang +, and Anwar Walid Electrical Engineering,
More informationCS 343: Artificial Intelligence
CS 343: Artificial Intelligence Markov Decision Processes II Prof. Scott Niekum The University of Texas at Austin [These slides based on those of Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC
More informationarxiv: v3 [cs.lg] 22 Feb 2017
Options Discovery with Budgeted Reinforcement Learning Aurélia Léon and Ludovic Denoyer Sorbonne Universités, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France {aurelia.leon,ludovic.denoyer}@lip6.fr
More informationMonte-Carlo Planning: Introduction and Bandit Basics. Alan Fern
Monte-Carlo Planning: Introduction and Bandit Basics Alan Fern 1 Large Worlds We have considered basic model-based planning algorithms Model-based planning: assumes MDP model is available Methods we learned
More informationTaxing Firms Facing Financial Frictions
Taxing Firms Facing Financial Frictions Daniel Wills 1 Gustavo Camilo 2 1 Universidad de los Andes 2 Cornerstone November 11, 2017 NTA 2017 Conference Corporate income is often taxed at different sources
More informationGMM for Discrete Choice Models: A Capital Accumulation Application
GMM for Discrete Choice Models: A Capital Accumulation Application Russell Cooper, John Haltiwanger and Jonathan Willis January 2005 Abstract This paper studies capital adjustment costs. Our goal here
More informationPortfolio Management and Optimal Execution via Convex Optimization
Portfolio Management and Optimal Execution via Convex Optimization Enzo Busseti Stanford University April 9th, 2018 Problems portfolio management choose trades with optimization minimize risk, maximize
More informationIntro to Reinforcement Learning. Part 3: Core Theory
Intro to Reinforcement Learning Part 3: Core Theory Interactive Example: You are the algorithm! Finite Markov decision processes (finite MDPs) dynamics p p p Experience: S 0 A 0 R 1 S 1 A 1 R 2 S 2 A 2
More informationInformation Aggregation in Dynamic Markets with Strategic Traders. Michael Ostrovsky
Information Aggregation in Dynamic Markets with Strategic Traders Michael Ostrovsky Setup n risk-neutral players, i = 1,..., n Finite set of states of the world Ω Random variable ( security ) X : Ω R Each
More informationMarkov Decision Processes
Markov Decision Processes Ryan P. Adams COS 324 Elements of Machine Learning Princeton University We now turn to a new aspect of machine learning, in which agents take actions and become active in their
More informationMonte-Carlo Planning: Introduction and Bandit Basics. Alan Fern
Monte-Carlo Planning: Introduction and Bandit Basics Alan Fern 1 Large Worlds We have considered basic model-based planning algorithms Model-based planning: assumes MDP model is available Methods we learned
More informationthen for any deterministic f,g and any other random variable
Martingales Thursday, December 03, 2015 2:01 PM References: Karlin and Taylor Ch. 6 Lawler Sec. 5.1-5.3 Homework 4 due date extended to Wednesday, December 16 at 5 PM. We say that a random variable is
More informationCompound Reinforcement Learning: Theory and An Application to Finance
Compound Reinforcement Learning: Theory and An Application to Finance Tohgoroh Matsui 1, Takashi Goto 2, Kiyoshi Izumi 3,4, and Yu Chen 3 1 Chubu University, 1200 Matsumoto-cho, Kasugai, 487-8501 Aichi,
More informationSTATE UNIVERSITY OF NEW YORK AT ALBANY Department of Economics. Ph. D. Comprehensive Examination: Macroeconomics Fall, 2010
STATE UNIVERSITY OF NEW YORK AT ALBANY Department of Economics Ph. D. Comprehensive Examination: Macroeconomics Fall, 2010 Section 1. (Suggested Time: 45 Minutes) For 3 of the following 6 statements, state
More informationCS 188: Artificial Intelligence Fall 2011
CS 188: Artificial Intelligence Fall 2011 Lecture 9: MDPs 9/22/2011 Dan Klein UC Berkeley Many slides over the course adapted from either Stuart Russell or Andrew Moore 2 Grid World The agent lives in
More informationMarkov Decision Processes (MDPs) CS 486/686 Introduction to AI University of Waterloo
Markov Decision Processes (MDPs) CS 486/686 Introduction to AI University of Waterloo Outline Sequential Decision Processes Markov chains Highlight Markov property Discounted rewards Value iteration Markov
More informationReinforcement Learning Analysis, Grid World Applications
Reinforcement Learning Analysis, Grid World Applications Kunal Sharma GTID: ksharma74, CS 4641 Machine Learning Abstract This paper explores two Markov decision process problems with varying state sizes.
More informationComplex Decisions. Sequential Decision Making
Sequential Decision Making Outline Sequential decision problems Value iteration Policy iteration POMDPs (basic concepts) Slides partially based on the Book "Reinforcement Learning: an introduction" by
More informationCS 188: Artificial Intelligence. Outline
C 188: Artificial Intelligence Markov Decision Processes (MDPs) Pieter Abbeel UC Berkeley ome slides adapted from Dan Klein 1 Outline Markov Decision Processes (MDPs) Formalism Value iteration In essence
More informationMaking Decisions. CS 3793 Artificial Intelligence Making Decisions 1
Making Decisions CS 3793 Artificial Intelligence Making Decisions 1 Planning under uncertainty should address: The world is nondeterministic. Actions are not certain to succeed. Many events are outside
More informationMarket MicroStructure Models. Research Papers
Market MicroStructure Models Jonathan Kinlay Summary This note summarizes some of the key research in the field of market microstructure and considers some of the models proposed by the researchers. Many
More informationChapter 6: Temporal Difference Learning
Chapter 6: emporal Difference Learning Objectives of this chapter: Introduce emporal Difference (D) learning Focus first on policy evaluation, or prediction, methods hen extend to control methods by following
More informationCS 188 Fall Introduction to Artificial Intelligence Midterm 1. ˆ You have approximately 2 hours and 50 minutes.
CS 188 Fall 2013 Introduction to Artificial Intelligence Midterm 1 ˆ You have approximately 2 hours and 50 minutes. ˆ The exam is closed book, closed notes except your one-page crib sheet. ˆ Please use
More informationGeneralized Multi-Factor Commodity Spot Price Modeling through Dynamic Cournot Resource Extraction Models
Generalized Multi-Factor Commodity Spot Price Modeling through Dynamic Cournot Resource Extraction Models Bilkan Erkmen (joint work with Michael Coulon) Workshop on Stochastic Games, Equilibrium, and Applications
More informationThe exam is closed book, closed calculator, and closed notes except your one-page crib sheet.
CS 188 Spring 2015 Introduction to Artificial Intelligence Midterm 1 You have approximately 2 hours and 50 minutes. The exam is closed book, closed calculator, and closed notes except your one-page crib
More information