TEXPLORE: Temporal Difference Reinforcement Learning for Robots and Time-Constrained Domains

✍ Scribed by Todd Hester (auth.)

Publisher: Springer International Publishing
Year: 2013
Tongue: English
Leaves: 170
Series: Studies in Computational Intelligence 503
Edition: 1
Category: Library

No coin nor oath required. For personal study only.

✦ Synopsis

This book presents and develops new reinforcement learning methods that enable fast and robust learning on robots in real-time.

Robots have the potential to solve many problems in society, because of their ability to work in dangerous places doing necessary jobs that no one wants or is able to do. One barrier to their widespread deployment is that they are mainly limited to tasks where it is possible to hand-program behaviors for every situation that may be encountered. For robots to meet their potential, they need methods that enable them to learn and adapt to novel situations that they were not programmed for. Reinforcement learning (RL) is a paradigm for learning sequential decision making processes and could solve the problems of learning and adaptation on robots. This book identifies four key challenges that must be addressed for an RL algorithm to be practical for robotic control tasks. These RL for Robotics Challenges are: 1) it must learn in very few samples; 2) it must learn in domains with continuous state features; 3) it must handle sensor and/or actuator delays; and 4) it should continually select actions in real time. This book focuses on addressing all four of these challenges. In particular, this book is focused on time-constrained domains where the first challenge is critically important. In these domains, the agent’s lifetime is not long enough for it to explore the domains thoroughly, and it must learn in very few samples.

✦ Table of Contents

Front Matter....Pages 1-11
Introduction....Pages 1-9
Background and Problem Specification....Pages 11-23
Real Time Architecture....Pages 25-34
The TEXPLORE Algorithm....Pages 35-49
Empirical Evaluation....Pages 51-84
Further Examination of Exploration....Pages 85-119
Related Work....Pages 121-135
Discussion and Conclusion....Pages 137-147
Back Matter....Pages 149-164

✦ Subjects

Computational Intelligence; Image Processing and Computer Vision; Robotics and Automation

📜 SIMILAR VOLUMES

Reinforcement Learning and Decision Maki

📁 Reinforcement Learning and Decision Making - Algorithms, Markov Decision Processes (MDPs), Temporal Difference (TD) Lambda, Convergence, Analysis, Exploration, Exploitation, Generalisation, Game Theory, Coordinating, Communicating, Coaching (CCC)

✍ Various 📂 Library 🌐 English

Mathematical population dynamics and epi

📁 Mathematical population dynamics and epidemiology in temporal and spatio-temporal domains

✍ Dhar, Joydip; Singh, Harkaran 📂 Library 📅 2019 🏛 Apple Academic Press;CRC 🌐 English

"In todays era, the spread of diseases happens very quickly as a large population migrates from one part to another of the world with the readily available transportation facilities. In this century, mankind faces even more challenging environment- and health-related problems than ever before. There

Transfer in Reinforcement Learning Domai

📁 Transfer in Reinforcement Learning Domains

✍ Matthew E. Taylor (auth.) 📂 Library 📅 2009 🏛 Springer-Verlag Berlin Heidelberg 🌐 English

<p><P>In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often

Explainable and Interpretable Reinforcem

📁 Explainable and Interpretable Reinforcement Learning for Robotics (Synthesis Lectures on Artificial Intelligence and Machine Learning)

✍ Aaron M. Roth, Dinesh Manocha, Ram D. Sriram, Elham Tabassi 📂 Library 📅 2024 🏛 Springer 🌐 English

<p><span>This book surveys the state of the art in explainable and interpretable reinforcement learning (RL) as relevant for robotics. While RL in general has grown in popularity and been applied to increasingly complex problems, several challenges have impeded the real-world adoption of RL algorith

Explainable and Interpretable Reinforcem

📁 Explainable and Interpretable Reinforcement Learning for Robotics (Synthesis Lectures on Artificial Intelligence and Machine Learning)

✍ Aaron M. Roth, Dinesh Manocha, Ram D. Sriram, Elham Tabassi 📂 Library 📅 2024 🏛 Springer 🌐 English

Domain-sensitive Temporal Tagging

📁 Domain-sensitive Temporal Tagging

✍ Jannik Strötgen, Michael Gertz 📂 Library 📅 2016 🏛 Morgan & Claypool 🌐 English