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
10 Jul 1994
TL;DR: In this paper, the authors propose a methodology for designing reinforcement functions that take advantage of implicit domain knowledge in order to accelerate learning in such domains, which involves the use of heterogeneous reinforcement functions and progress estimators.
Abstract: This paper discusses why traditional reinforcement learning methods, and algorithms applied to those models, result in poor performance in situated domains characterized by multiple goals, noisy state, and inconsistent reinforcement. We propose a methodology for designing reinforcement functions that take advantage of implicit domain knowledge in order to accelerate learning in such domains. The methodology involves the use of heterogeneous reinforcement functions and progress estimators, and applies to learning in domains with a single agent or with multiple agents. The methodology is experimentally validated on a group of mobile robots learning a foraging task.
427 citations
TL;DR: Both the role of pharmacological inhibition or lesion of dopaminergic neuron function and the involvement of dopamine in reward prediction for the purpose of reward seeking can be captured in a single computational model.
422 citations
Proceedings Article•
01 Jan 1989
TL;DR: It is shown that once the output layer of a multilayer perceptron is modified to provide mathematically correct probability distributions, and the usual squared error criterion is replaced with a probability-based score, the result is equivalent to Maximum Mutual Information training.
Abstract: One of the attractions of neural network approaches to pattern recognition is the use of a discrimination-based training method. We show that once we have modified the output layer of a multilayer perceptron to provide mathematically correct probability distributions, and replaced the usual squared error criterion with a probability-based score, the result is equivalent to Maximum Mutual Information training, which has been used successfully to improve the performance of hidden Markov models for speech recognition. If the network is specially constructed to perform the recognition computations of a given kind of stochastic model based classifier then we obtain a method for discrimination-based training of the parameters of the models. Examples include an HMM-based word discriminator, which we call an 'Alphanet'.
422 citations
"Reinforcement Learning: An Introduc..." refers background in this paper
...9) is due to Bridle (1990). This rule appears to have been first proposed by Luce (1959)....
[...]
TL;DR: It is suggested that, in a statistical account of conditioning, surprise signals change and therefore uncertainty and the need for new learning, and how these phenomena help constrain statistical theories of animal and human learning.
419 citations
01 Jan 1990
TL;DR: A method of learning is presented in which all the experiences in the lifetime of the robot are explicitly remembered, thus permitting very quick predictions of the e ects of proposed actions and, given a goal behaviour, permitting fast generation of a candidate action.
Abstract: This dissertation is about the application of machine learning to robot control. A system which has no initial model of the robot/world dynamics should be able to construct such a model using data received through its sensors|an approach which is formalized here as the SAB (State-ActionBehaviour) control cycle. A method of learning is presented in which all the experiences in the lifetime of the robot are explicitly remembered. The experiences are stored in a manner which permits fast recall of the closest previous experience to any new situation, thus permitting very quick predictions of the e ects of proposed actions and, given a goal behaviour, permitting fast generation of a candidate action. The learning can take place in high-dimensional non-linear control spaces with real-valued ranges of variables. Furthermore, the method avoids a number of shortcomings of earlier learning methods in which the controller can become trapped in inadequate performance which does not improve. Also considered is how the system is made resistant to noisy inputs and how it adapts to environmental changes. A well founded mechanism for choosing actions is introduced which solves the experiment/perform dilemma for this domain with adequate computational e ciency, and with fast convergence to the goal behaviour. The dissertation explains in detail how the SAB control cycle can be integrated into both low and high complexity tasks. The methods and algorithms are evaluated with numerous experiments using both real and simulated robot domains. The nal experiment also illustrates how a compound learning task can be structured into a hierarchy of simple learning tasks.
415 citations
"Reinforcement Learning: An Introduc..." refers background or methods in this paper
...4 Prioritized sweeping was developed simultaneously and independently by Moore and Atkeson (1993) and Peng and Williams (1993)....
[...]
...4 Prioritized sweeping was developed simultaneously and independently by Moore and Atkeson (1993) and Peng and Williams (1993). The results in Figure 8....
[...]
...4 Prioritized sweeping was developed simultaneously and independently by Moore and Atkeson (1993) and Peng and Williams (1993). The results in Figure 8.7 are due to Peng and Williams (1993). The results in Figure 8....
[...]
...Reynolds and Wickens (2002) proposed a three-factor rule for synaptic plasticity in the corticostriatal pathway in which dopamine modulates changes in corticostriatal synaptic efficacy. They discussed the experimental support for this kind of learning rule and its possible molecular basis. The definitive demonstration of spike-timing-dependent plasticity (STDP) is attributed to Markram, Lübke, Frotscher, and Sakmann (1997), with evidence from earlier experiments by Levy and Steward (1983) and others that the relative timing of pre- and postsynaptic spikes is critical for inducing changes in synaptic efficacy....
[...]
...example is based on a similar task studied by Moore (1990). The results on it presented in Figure 10....
[...]