IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2007)

Fitted Q Iteration with CMACs...1

Stephan Timmer and Martin Riedmiller

Reinforcement-Learning-based Magneto-Hydrodynamic Control of Hypersonic Flows...9

Nilesh Kulkarni and Minh Phan

A Novel Fuzzy Reinforcement Learning Approach in Two-Level Intelligent Control of 3-DOF Robot Manipulators...20

Nasser Sadati and Mohammad Mollaie Emamzadeh

Knowledge Transfer using Local Features...26

Martin Stolle and Christopher Atkeson

Particle Swarm Optimized Adaptive Dynamic Programming...32

Dongbin Zhao, Jianqiang Yi and Derong Liu

Discrete-time nonlinear HJB solution using Approximate dynamic programming: Convergence Proof...38

Asma AL Tamimi and Frank Lewis

Dual Representations for Dynamic Programming and Reinforcement Learning...44

Tao Wang, Michael Bowling and Dale Schuurmans

An Optimal ADP Algorithm for a High-Dimensional Stochastic Control Problem...52

Juliana Nascimento and Warren Powell

Convergence of Model-Based Temporal Difference Learning for Control...60

Hado van Hasselt and Marco Wiering

On a Successful Application of Multi-Agent Reinforcement Learning to Operations Research Benchmarks...68

Thomas Gabel and Martin Riedmiller

The Effect of Bootstrapping in Multi-Automata Reinforcement Learning...76

Maarten Peeters, Katja Verbeeck and Ann Nowe

A Theoretical Analysis of Cooperative Behavior in Multi-agent Q-learning...84

Ludo Waltman and Uzay Kaymak

Hybrid Ant Colony Optimization Using Memetic Algorithm for Traveling Salesman Problem...92

Haibin Duan and Xiufen Yu

Robust Dynamic Programming for Discounted Infinite-Horizon Markov Decision Processes with Uncertain Stationary Transition Matrices...96

Baohua Li and Jennie Si

Model-Based Reinforcement Learning in Factored-State MDPs...103

Alexander Strehl

Leader-Follower semi-Markov Decision Problems: Theoretical Framework and Approximate Solution...111

Kurian Tharakunnel and Siddhartha Bhattacharyya

A Scalable Recurrent Neural Network Framework for Model-Free POMDPs...119

Zhenzhen Liu and Itamar Elhanany

Reinforcement learning by backpropagation through an LSTM model/critic...127

Bram Bakker

Discrete-Time Approximate Dynamic Programming using Wavelet Basis Function Neural Networks...135

Ning Jin, Derong Liu, Ting Huang and Zhongyu Pang

The Knowledge Gradient Policy for Offline Learning with Independent Normal Rewards...143

Peter Frazier and Warren Powell

A Recurrent Control Neural Network for Data Efficient Reinforcement Learning...151

Anton Schaefer, Steffen Udluft and Hans-Georg Zimmermann

Computing Optimal Stationary Policies for Multi-Objective Markov Decision Processes...158

Marco Wiering and Edwin De Jong

Strategy Generation with Cognitive Distance in Two-Player Games...166

Kosuke Sekiyama, Ricardo Carnieri and Toshio Fukuda

Identifying Trajectory Classes in Dynamic Tasks...172

Stuart Anderson and Siddhartha Srinivasa

A Dynamic Programming Approach to Viability Problems...178

Pierre-Arnaud Coquelin, Sophie Martin and Remi Munos

Randomly Sampling Actions In Dynamic Programming...185

Christopher Atkeson

SVM Viability Controller Active Learning: Application to Bike Control...193

Laetitia Chapel and Guillaume Deffuant

An Approximate Dynamic Programming Approach for Job Releasing and Sequencing in a Reentrant Manufacturing Line...201

Jose Ramirez-Hernandez and Emmanuel Fernandez

Using ADP to Understand and Replicate Brain Intelligence: the Next Level Design...209

Paul Werbos

Opposition-Based Reinforcement Learning in the Management of Water Resources...217

Hamid R. Tizhoosh, Masoud Mahootchi and K. Ponnambalam

Online Reinforcement Learning Neural Network Controller Design for Nanomanipulation...225

Qinmin Yang and Sarangapani Jagannathan

Short-term Stock Market Timing Prediction under Reinforcement Learning Schemes...233

Hailin Li, Cihan Dagli and David Enke

Dynamic optimization of the strength ratio during a terrestrial conflict...241

Alexandre Sztykgold, Gilles Coppin and Olivier Hudry

Continuous-Time ADP for Linear Systems with Partially Unknown Dynamics...247

Draguna Vrabie, Murad Abu-Khalaf, Frank L. Lewis and Youyi Wang

Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark...254

Martin Riedmiller, Jan Peters and Stefan Schaal

Using Reward-weighted Regression for Reinforcement Learning of Task Space Control...262

Jan Peters and Stefan Schaal

Toward effective combination of off-line and on-line training in ADP framework...268

Danil Prokhorov

Reinforcement Learning in Continuous Action Spaces...272

Hado van Hasselt and Marco Wiering

Two Novel On-policy Reinforcement Learning Algorithms based on TD(λ)-methods...280

Marco Wiering and Hado van Hasselt

Opposition-Based Q(λ) with Non-Markovian Update...288

Hamid R. Tizhoosh, Maryam Shokri and Mohamed S. Kamel

Coordinated Reinforcement Learning for Decentralized Optimal Control...296

Daniel Yagan and Chen-Khong Tham

An Approximate Dynamic Programming Strategy for Responsive Traffic Signal Control...303

Chen Cai

DHP Adaptive Critic Motion Control of Autonomous Wheeled Mobile Robot...311

Wei-Song Lin and Ping-Chieh Yang

Approximate Optimal Control-Based Neurocontroller with a State Observation System for Seedlings Growth in Greenhouse...318

Daniel Patino, Julian Pucheta, Carlos Schugurensky, Rogelio Fullana and Benjamin Kuchen

Efficient Learning in Cellular Simultaneous Recurrent Neural Networks - The Case of Maze Navigation Problem...324

Roman Ilin, Robert Kozma and Paul Werbos

Value-Iteration Based Fitted Policy Iteration: Learning with a Single Trajectory...330

Andras Antos, Szepesvari Csaba and Munos Remi

Kernelizing LSPE(λ)...338

Tobias Jung and Daniel Polani

Q-learning algorithm with continuous state spaces and finite decision set...346

Kengy Barty, Pierre Girardeau, Jean Sebastien Roy and Cyrille Strugarek

Sparse Temporal Difference Learning using LASSO...352

Manuel Loth, Manuel Davy and Philippe Preux