This paper examines whether temporal difference methods for training connectionist networks, such as Sutton's TD(λ) algorithm, can be successfully applied to complex real-world problems. A number of important practical issues are identified and discussed from a general theoretical perspective. These practical issues are then examined in the context of a case study in which TD(λ) is applied to learning the game of backgammon from the outcome of self-play. This is apparently the first application of this algorithm to a complex non-trivial task. It is found that, with zero knowledge built in, the network is able to learn from scratch to play the entire game at a fairly strong intermediate level of performance, which is clearly better than conventional commercial programs, and which in fact surpasses comparable networks trained on a massive human expert data set.

Comments:!! See this http URL for any accompanying files

This is a summary of results with Dyna, a class of architectures for intelligent systems based on approximating dynamic programming methods. Dyna architectures integrate trial-and-error (reinforcement) learning and execution-time planning into a single process operating alternately on the world and on a learned forward model of the world. We describe and show results for two Dyna architectures, Dyna-AHC and Dyna-Q. Using a navigation task, results are shown for a simple Dyna-AHC system which simultaneously learns by trial and error, learns a world model, and plans optimal routes using the evolving world model. We show that Dyna-Q architectures (based on Watkins's Q-Iearning) are easy to adapt for use in changing environments.

This work addresses three problems with reinforcement learning and adaptive neuro-control: 1. Non-Markovian interfaces between learner and environment.

However, a large class of continuous control problems require maintaining the system at a desired operating point, or setpoint, at a given time. We refer to this problem as the basic setpoint control problem [Guha 90], and have shown that reinforcement learning can be used, not surprisingly, quite well for such control tasks.

This is a summary of results with Dyna, a class of architectures for intelligent systems based on approximating dynamic programming methods. Dyna architectures integrate trial-and-error (reinforcement) learning and execution-time planning into a single process operating alternately on the world and on a learned forward model of the world. We describe and show results for two Dyna architectures, Dyna-AHC and Dyna-Q. Using a navigation task, results are shown for a simple Dyna-AHC system which simultaneously learns by trial and error, learns a world model, and plans optimal routes using the evolving world model. We show that Dyna-Q architectures (based on Watkins's Q-Iearning) are easy to adapt for use in changing environments.

Barto, Sutton and Watkins [2] introduced a grid task as a didactic example of temporal difference planning and asynchronous dynamical pre gramming. This paper considers the effects of changing the coding of the input stimulus, and demonstrates that the self-supervised learning of a particular form of hidden unit representation improves performance.

Barto, Sutton and Watkins [2] introduced a grid task as a didactic example of temporal difference planning and asynchronous dynamical pre gramming. This paper considers the effects of changing the coding of the input stimulus, and demonstrates that the self-supervised learning of a particular form of hidden unit representation improves performance.

This work addresses three problems with reinforcement learning and adaptive neuro-control: 1. Non-Markovian interfaces between learner and environment.

However, a large class of continuous control problems require maintaining the system at a desired operating point, or setpoint, at a given time. We refer to this problem as the basic setpoint control problem [Guha 90], and have shown that reinforcement learning can be used, not surprisingly, quite well for such control tasks.