# 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

#### Figures, Tables, and Topics from this paper

#### 7,014 Citations

Reinforcement Learning: A Review from a Machine Learning Perspective

- Computer Science
- 2014

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

- Computer Science
- IEEE Transactions on Neural Networks
- 2005

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

- Computer Science
- 2013

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

- Computer Science
- 2015

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

- Computer Science
- Algorithms for Reinforcement Learning
- 2010

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

- Computer Science
- ArXiv
- 2020

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

- 2014

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 get… Expand

A survey of inverse reinforcement learning techniques

- Computer Science
- 2012

The original IRL algorithms and its close variants, as well as their recent advances are reviewed and compared. Expand

Reinforcement Learning in R

- Computer Science, Mathematics
- ArXiv
- 2018

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

- Computer Science
- Int. J. Intell. Comput. Cybern.
- 2012

The original IRL algorithms and its close variants, as well as their recent advances are reviewed and compared. Expand

#### References

SHOWING 1-10 OF 239 REFERENCES

Reinforcement learning for robots using neural networks

- Computer Science
- 1992

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

- Computer Science
- IJCAI
- 1991

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

- Computer Science
- 1992

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

- 1994

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 the… Expand

Learning in embedded systems

- Computer Science
- 1993

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

- Computer Science
- ICML
- 1994

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)

- Computer Science
- 1986

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

- Computer Science
- NIPS
- 1989

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

- Computer Science
- 1994

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

- Computer Science
- COLT '94
- 1994

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