Reinforcement Learning: A Survey

@article{Kaelbling1996ReinforcementLA,
  title={Reinforcement Learning: A Survey},
  author={L. Kaelbling and M. Littman and A. Moore},
  journal={J. Artif. Intell. Res.},
  year={1996},
  volume={4},
  pages={237-285}
}
This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in… Expand
Reinforcement Learning: A Review from a Machine Learning Perspective
TLDR
This paper provides the overview of Reinforcement Learning from Machine learning perspective, and presents nature of RL problems, with focus on some influential model free RL algorithms, challenges and recent trends in theory and practice. Expand
Reinforcement Learning: An Introduction
TLDR
This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications. Expand
Use of Reinforcement Learning as a Challenge: A Review
TLDR
This paper discusses its basic model, the optimal policies used in RL, the main reinforcement optimal policy that are used to reward the agent including model free and model based policies, and some of the future research scope in Reinforcement Learning. Expand
Control Optimization with Reinforcement Learning
TLDR
This chapter focuses on a relatively new methodology called reinforcement learning (RL), a form of simulation-based dynamic programming, primarily used for solving Markov and semi-Markov decision problems. Expand
Algorithms for Reinforcement Learning
TLDR
This book focuses on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming, and gives a fairly comprehensive catalog of learning problems, and describes the core ideas, followed by the discussion of their theoretical properties and limitations. Expand
A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions
TLDR
A framework for the presentation of available methods of reinforcement learning is provided that is informative enough and simple to follow for the new researchers and academics in this domain considering the latest concerns. Expand
REINFORCEMENT LEARNING IN COMPLEX REAL WORLD DOMAINS: A REVIEW
Reinforcement Learning is an area of Machine Learning inspired by behaviorist psychology based on the mechanism of learning from rewards. RL does not require prior knowledge and automatically getExpand
A survey of inverse reinforcement learning techniques
TLDR
The original IRL algorithms and its close variants, as well as their recent advances are reviewed and compared. Expand
Reinforcement Learning in R
TLDR
This paper demonstrates how to perform reinforcement learning in R and introduces the ReinforcementLearning package, which provides a remarkably flexible framework and is easily applied to a wide range of different problems. Expand
A survey of inverse reinforcement learning techniques
TLDR
The original IRL algorithms and its close variants, as well as their recent advances are reviewed and compared. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 239 REFERENCES
Reinforcement learning for robots using neural networks
TLDR
This dissertation concludes that it is possible to build artificial agents than can acquire complex control policies effectively by reinforcement learning and enable its applications to complex robot-learning problems. Expand
Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons
TLDR
This paper describes the input generalization problem (whereby the system must generalize to produce similar actions in similar situations) and an implemented solution, the G algorithm, which is based on recursive splitting of the state space based on statistical measures of differences in reinforcements received. Expand
Memory Approaches to Reinforcement Learning in Non-Markovian Domains
TLDR
This paper studies three connectionist approaches which learn to use history to handle perceptual aliasing: the window-Q, recurrent- Q, and recurrent-model architectures. Expand
Eecient Reinforcement Learning
In this paper we propose a new formal model for studying reinforcement learning, based on Valiant's PAC framework. In our model the learner does not have direct access to every state of theExpand
Learning in embedded systems
TLDR
This dissertation addresses the problem of designing algorithms for learning in embedded systems using Sutton's techniques for linear association and reinforcement comparison, while the interval estimation algorithm uses the statistical notion of confidence intervals to guide its generation of actions. Expand
To Discount or Not to Discount in Reinforcement Learning: A Case Study Comparing R Learning and Q Learning
TLDR
It is argued for using medians over means as a better distribution-free estimator of average performance, and a simple non-parametric significance test for comparing learning data from two RL techniques is described. Expand
Learning and problem-solving with multilayer connectionist systems (adaptive, strategy learning, neural networks, reinforcement learning)
TLDR
A novel algorithm is examined that combines ASPECTS of REINFORCEMENT LEARNING and a DATA-DIRECTED SEARCH for USEFUL WEIGHTS, and is shown to out perform reinFORMCEMENT-LEARNING ALGORITHMS. Expand
Generalization and Scaling in Reinforcement Learning
TLDR
This paper describes a neural network algorithm called complementary reinforcement back-propagation (CRBP), and reports simulation results on problems designed to offer differing opportunities for generalization. Expand
On-line Q-learning using connectionist systems
TLDR
Simulations show that on-line learning algorithms are less sensitive to the choice of training parameters than backward replay, and that the alternative update rules of MCQ-L and Q( ) are more robust than standard Q-learning updates. Expand
Efficient reinforcement learning
TLDR
A new formal model for studying reinforcement learning, based on Valiant's PAC framework, that requires the learner to produce a policy whose expected value from the initial state is ε-close to that of the optimal policy, with probability no less than 1−δ. Expand
...
1
2
3
4
5
...