In which we try to give a basic intuitive sense of what reinforcement learning is and how it differs and relates to other fields, e.g., supervised learning and neural networks, genetic algorithms and artificial life, control theory. Intuitively, RL is trial and error (variation and selection, search) plus learning (association, memory). We argue that RL is the only field that seriously addresses the special features of the problem of learning from interaction to achieve long-term goals.

This article introduces a class of incremental learning procedures specialized for prediction – that is, for using past experience with an incompletely known system to predict its future behavior. Whereas conventional prediction-learning methods assign credit by means of the difference between predicted and actual outcomes, the new methods assign credit by means of the difference between temporally successive predictions. Although such temporal-difference methods have been used in Samuel's checker player, Holland's bucket brigade, and the author's Adaptive Heuristic Critic, they have remained poorly understood. Here we prove their convergence and optimality for special cases and relate them to supervised-learning methods. For most real-world prediction problems, temporal-difference methods require less memory and less peak computation than conventional methods and they produce more accurate predictions. We argue that most problems to which supervised learning is currently applied are really prediction problems of the sort to which temporal-difference methods can be applied to advantage.

Abstract not found

On large problems, reinforcement learning systems must use parameterized function approximators such as neural networks in order to generalize between similar situations and actions. In these cases there are no strong theoretical results on the accuracy of convergence, and computational results have been mixed. In particular, Boyan and Moore reported at last year's meeting a series of negative results in attempting to apply dynamic programming together with function approximation to simple control problems with continuous state spaces. In this paper, we present positive results for all the control tasks they attempted, and for one that is significantly larger. The most important differences are that we used sparse-coarse-coded function approximators (CMACs) whereas they used mostly global function approximators, and that we learned online whereas they learned offline. Boyan and Moore and others have suggested that the problems they encountered could be solved by using actual outcomes (...

A major goal of research on networks of neuron-like processing units is to discover efficient learning procedures that allow these networks to construct complex internal representations of their environment. The learning procedures must be capable of modifying the connection strengths in such a way that internal units which are not part of the input or output come to represent important features of the task domain. Several interesting gradient-descent procedures have recently been discovered. Each connection computes the derivative, with respect to the connection strength, of a global measure of the error in the performance of the network. The strength is then adjusted in the direction that decreases the error. These relatively simple, gradient-descent learning procedures work well for small tasks and the new challenge is to find ways of improving their convergence rate and their generalization abilities so that they can be applied to larger, more realistic tasks.

Function approximation is essential to reinforcement learning, but the standard approach of approximating a value function and determining a policy from it has so far proven theoretically intractable. In this paper we explore an alternative approach in which the policy is explicitly represented by its own function approximator, independent of the value function, and is updated according to the gradient of expected reward with respect to the policy parameters. Williams’s REINFORCE method and actor–critic methods are examples of this approach. Our main new result is to show that the gradient can be written in a form suitable for estimation from experience aided by an approximate action-value or advantage function. Using this result, we prove for the first time that a version of policy iteration with arbitrary differentiable function approximation is convergent to a locally optimal policy.

Abstract. This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units. These algorithms, called REINFORCE algorithms, are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement in both immediate-reinforcement tasks and certain limited forms of delayed-reinforcement tasks, and they do this without explicitly computing gradient estimates or even storing information from which such estimates could be computed. Specific examples of such algorithms are presented, some of which bear a close relationship to certain existing algorithms while others are novel but potentially interesting in their own right. Also given are results that show how such algorithms can be naturally integrated with backpropagation. We close with a brief discussion of a number of additional issues surrounding the use of such algorithms, including what is known about their limiting behaviors as well as further considerations that might be used to help develop similar but potentially more powerful reinforcement learning algorithms.

In this report we show how the class of adaptive prediction methods that Sutton called "temporal difference," or TD, methods are related to the theory of squential decision making. TD methods have been used as "adaptive critics" in connectionist learning systems, and have been proposed as models of animal learning in classical conditioning experiments. Here we relate TD methods to decision tasks formulated in terms of a stochastic dynamical system whose behavior unfolds over time under the influence of a decision maker's actions. Strategies are sought for selecting actions so as to maximize a measure of long-term payoff gain. Mathematically, tasks such as this can be formulated as Markovian decision problems, and numerous methods have been proposed for learning how to solve such problems. We show how a TD method can be understood as a novel synthesis of concepts from the theory of stochastic dynamic programming, which comprises the standard method for solving such tasks when a model of the dynamical system is available, and the theory of parameter estimation, which provides the appropriate context for studying learning rules in the form of equations for updating associative strengths in behavioral models, or connection weights in connectionist networks. Because this report is oriented primarily toward the non-engineer interested in animal learning, it presents tutorials on stochastic sequential decision tasks, stochastic dynamic programming, and parameter estimation.

. The eligibility trace is one of the basic mechanisms used in reinforcement learning to handle delayed reward. In this paper we introduce a new kind of eligibility trace, the replacing trace, analyze it theoretically, and show that it results in faster, more reliable learning than the conventional trace. Both kinds of trace assign credit to prior events according to how recently they occurred, but only the conventional trace gives greater credit to repeated events. Our analysis is for conventional and replace-trace versions of the offline TD(1) algorithm applied to undiscounted absorbing Markov chains. First, we show that these methods converge under repeated presentations of the training set to the same predictions as two well known Monte Carlo methods. We then analyze the relative efficiency of the two Monte Carlo methods. We show that the method corresponding to conventional TD is biased, whereas the method corresponding to replace-trace TD is unbiased. In addition, we show that t...

This thesis addresses situated, embodied agents interacting in complex domains. It focuses on two problems: 1) synthesis and analysis of intelligent group behavior, and 2) learning in complex group environments. Basic behaviors, control laws that cluster constraints to achieve particular goals and have the appropriate compositional properties, are proposed as effective primitives for control and learning. The thesis describes the process of selecting such basic behaviors, formally specifying them, algorithmically implementing them, and empirically evaluating them. All of the proposed ideas are validated with a group of up to 20 mobile robots using a basic behavior set consisting of: safe--wandering, following, aggregation, dispersion, and homing. The set of basic behaviors acts as a substrate for achieving more complex high--level goals and tasks. Two behavior combination operators are introduced, and verified by combining subsets of the above basic behavior set to implement collective flocking, foraging, and docking. A methodology is introduced for automatically constructing higher--level behaviors