Book•
Reinforcement Learning: An Introduction
01 Jan 1988-
TL;DR: 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.
Abstract: Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.
Citations
More filters
Book•
[...]
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.
38,208 citations
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Abstract: The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
23,074 citations
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
14,635 citations
Cites background from "Reinforcement Learning: An Introduc..."
...Such NNs learn to perceive/encode/predict/ classify patterns or pattern sequences, but they do not learn to act in the more general sense of Reinforcement Learning (RL) in unknown environments (see surveys, e.g., Kaelbling et al., 1996; Sutton & Barto, 1998; Wiering & van Otterlo, 2012)....
[...]
...The latter is often explained in a probabilistic framework (e.g., Sutton & Barto, 1998), but its basic idea can already be conveyed in a deterministic setting....
[...]
...Such NNs learn to perceive / encode / predict / classify patterns or pattern sequences, but they do not learn to act in the more general sense of Reinforcement Learning (RL) in unknown environments (e.g., Kaelbling et al., 1996; Sutton and Barto, 1998)....
[...]
...Many variants of traditional RL exist (e.g., Barto et al., 1983; Watkins, 1989; Watkins and Dayan, 1992; Moore and Atkeson, 1993; Schwartz, 1993; Baird, 1994; Rummery and Niranjan, 1994; Singh, 1994; Baird, 1995; Kaelbling et al., 1995; Peng and Williams, 1996; Mahadevan, 1996; Tsitsiklis and van Roy, 1996; Bradtke et al., 1996; Santamarı́a et al., 1997; Prokhorov and Wunsch, 1997; Sutton and Barto, 1998; Wiering and Schmidhuber, 1998b; Baird and Moore, 1999; Meuleau et al., 1999; Morimoto and Doya, 2000; Bertsekas, 2001; Brafman and Tennenholtz, 2002; Abounadi et al., 2002; Lagoudakis and Parr, 2003; Sutton et al., 2008; Maei and Sutton, 2010)....
[...]
...This assumption does not hold in the broader fields of Sequential Decision Making and Reinforcement Learning (RL) (Kaelbling et al., 1996; Sutton and Barto, 1998; Hutter, 2005) (Sec....
[...]
TL;DR: Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.
Abstract: The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.
14,377 citations
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.
10,141 citations
References
More filters
Book•
01 Jun 2003
TL;DR: For undergraduate/graduate courses in Behavior Modification, Behavior Therapy, and Behavior Management, the authors of the first edition of the Principles of Behavior have sought to address a unique need of the students in their behavior modification classes: levels of student ability, experience, and exposure to the topics addressed in these courses often varied greatly.
Abstract: For undergraduate/graduate courses in Behavior Modification, Behavior Therapy, and Behavior Management.
This text offers a solid introduction to the principles of behavior using a clear, interesting, entertaining style with many case studies and everyday examples while maintaining a high level of intellectual rigor and addressing fundamental concepts.
Since writing the first edition of Principles of Behavior the authors have sought to address a unique need of the students in their behavior modification classes: levels of student ability, experience, and exposure to the topics addressed in these courses often varied greatly. From freshman undergradute courses straight through graduate level research, there was a need for a text that was flexible yet rigorous enough to appeal to both the novice and advanced student. Here, the authors have been able to do just that. Princibles of Behavior offers a solid introduction to the principles of behavior using a clear, interesting, entertaining style with many case studies and everyday examples while maintaining a high level of intellectual rigor and addressing fundamental concepts.
192 citations
TL;DR: It is shown that irregular spiking similar to that observed in biological neurons could be used as the basis for a learning rule that calculates a stochastic approximation to the gradient.
Abstract: Artificial neural networks are often trained by using the back propagation algorithm to compute the gradient of an objective function with respect to the synaptic strengths. For a biological neural network, such a gradient computation would be difficult to implement, because of the complex dynamics of intrinsic and synaptic conductances in neurons. Here we show that irregular spiking similar to that observed in biological neurons could be used as the basis for a learning rule that calculates a stochastic approximation to the gradient. The learning rule is derived based on a special class of model networks in which neurons fire spike trains with Poisson statistics. The learning is compatible with forms of synaptic dynamics such as short-term facilitation and depression. By correlating the fluctuations in irregular spiking with a reward signal, the learning rule performs stochastic gradient ascent on the expected reward. It is applied to two examples, learning the XOR computation and learning direction selectivity using depressing synapses. We also show in simulation that the learning rule is applicable to a network of noisy integrate-and-fire neurons.
190 citations
08 Mar 1999
TL;DR: The limitations of this approach are discussed, and an alternative is developed by extending Sutton''s work on linear systems to the general, nonlinear case, and the resulting online algorithms are computationally little more expensive than other acceleration techniques, and do not assume statistical independence between successive training patterns.
Abstract: Gain adaptation algorithms for neural networks typically adjust learning rates by monitoring the correlation between successive gradients. Here we discuss the limitations of this approach, and develop an alternative by extending Sutton''s work on linear systems to the general, nonlinear case. The resulting online algorithms are computationally little more expensive than other acceleration techniques, do not assume statistical independence between successive training patterns, and do not require an arbitrary smoothing parameter. In our benchmark experiments, they consistently outperform other acceleration methods, and show remarkable robustness when faced with non-i.i.d. sampling of the input space.
189 citations
27 Jun 1993
TL;DR: This paper presents a method by which a reinforcement learning agent can solve the incomplete perception problem using memory by using a hidden Markov model to represent its internal state space and creating memory capacity by splitting states of the HMM.
Abstract: This paper presents a method by which a reinforcement learning agent can solve the incomplete perception problem using memory. The agent uses a hidden Markov model (HMM) to represent its internal state space and creates memory capacity by splitting states of the HMM. The key idea is a test to determine when and how a state should be split: the agent only splits a state when doing so will help the agent predict utility. Thus the agent can create only as much memory as needed to perform the task at hand—not as much as would be required to model all the perceivable world. I call the technique UDM, for Utile Distinction Memory.
189 citations
01 Feb 1995
TL;DR: This work establishes the theoretical foundations of multi-scale models and derive TD algorithms for learning them and treats only the prediction problem--that of learning a model and value function for the case of fixed agent behavior.
Abstract: ARRAY(0x83fc18c) hierarchical or multi-level planning and reinforcement learning. In this paper we treat only the prediction problem--that of learning a model and value function for the case of fixed agent behavior. Within this context, we establish the theoretical foundations of multi-scale models and derive TD algorithms for learning them. Two small computational experiments are presented to test and illustrate the theory. This work is an extension and generalization of the work of Singh (1992), Dayan (1993), and Sutton and Pinette (1985).
188 citations
"Reinforcement Learning: An Introduc..." refers background in this paper
...The roots of variable γ are in the work on options (Sutton, Precup, and Singh, 1999) and its precursors (Sutton, 1995a), becoming explicit in the GQ(λ) paper (Maei and Sutton, 2010), which also introduced some of these recursive forms for the λ-returns....
[...]
...1 General value functions were first explicitly identified by Sutton and colleagues (Sutton, 1995a; Sutton et al., 2011; Modayil, White and Sutton, 2013)....
[...]