Solution of Delayed Reinforcement Learning Problems Having Continuous Action Spaces

Solution of Delayed Reinforcement Learning Problems Having Continuous Action Spaces (1996)

Cached

Download Links

by B. Ravindran

BibTeX

@MISC{Ravindran96solutionof,
    author = {B. Ravindran},
    title = {Solution of Delayed Reinforcement Learning Problems Having Continuous Action Spaces},
    year = {1996}
}

Bookmark

OpenURL

Abstract

This work concerns the solution of delayed Reinforcement Learning problems having continuous action spaces. The problems associated with continuous action spaces are discussed and various existing algorithms for solving the problem are presented. A extension of Q-learning for solving delayed RL problems having continuous action spaces is proposed which overcomes drawbacks associated with existing methods. Simulation results are presented to demonstrate the working of the proposed algorithm.

Citations

2716	Neural networks: A comprehensive foundation - Haykin - 1994
1964	Dynamic Programming - Bellman - 1957
1530	Introduction to the Theory of Neural Computation - Hertz, Krogh, et al. - 1991
665	Adaptive mixtures of local experts - Jacobs, Jordan, et al. - 1991
545	Some Studies in Machine Learning using the Game of Checkers - Samuel - 2000
427	Integrated architectures for learning, planning, and reacting based on approximating integrated architectures for learning, planning, and reacting based on approximating dynamic programming - Sutton - 1990
362	Real-time heuristic search - Korf - 1990
331	Dynamic Programming: Deterministic and Stochastic Models - Bertsekas - 1987
300	Generalization in reinforcement learning: Successful examples using sparse coarse coding - Sutton - 1996
288	Planning and Control - Dean, Wellman - 1991
280	Learning in embedded systems - Kaelbling - 1993
266	Dynamic Programming - Bertsekas - 1987
255	Self-improving reactive agents based on reinforcement learning, planning, and teaching - Lin - 1992
250	Improving elevator performance using reinforcement learning - Crites, Barto - 1996
247	Forward models: Supervised learning with a distal teacher - Jordan, Rumelhart - 1992
232	A New Approach to Manipulator control: the Cerebellar Model Articulation Controller - Albus - 1975
224	On-line Q-learning using connectionist systems - Rummery, Niranjan - 1994
222	Motivated reinforcement learning - Dayan - 2002
219	Temporal Credit Assignment in Reinforcement Learning - Sutton - 1984
203	The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces - Moore, Atkeson - 1995
196	Introduction to Stochastic Dynamic Programming - Ross - 1983
186	On the convergence of stochastic iterative dynamic programming algorithms - Jaakkola, Jordan, et al. - 1994
185	Learning and sequential decision making - Barto, Sutton - 1990
151	Transfer of learning by composing solutions of elemental sequential tasks - Singh - 1992
147	Learning to predict by the methods of temporal di erence - Sutton - 1988
144	Towards a modern theory of adaptive networks: expectation and prediction - Sutton, Barto - 1981
143	Learning Automata: An Introduction - Narendra, Thathachar - 1989
137	Reinforcement learning algorithm for partially observable Markov decision problems - Jaakkola, Singh, et al. - 1994
129	Vision, Instruction and Action - Chapman - 1991
129	Asynchronous stochastic approximation and Q-learning - Tsitsiklis - 1994
119	Feature-based methods for large scale dynamic programming - Tsitsiklis, Roy - 1996
117	input generalization in delayed reinforcement learning: an algorithm and performance comparisons - Chapman, Kaelbling
115	Learning without state-estimation in partially observable markovian decision processes - Singh, Jaakkola, et al. - 1994
113	Efficient exploration in reinforcement learning - Thrun - 1992
111	BOXES: An experiment in adaptive control - Michie, Chambers - 1968
106	Learning and Tuning Fuzzy Logic Controllers Through Reinforcements - Berenji, Khedkar - 1992
105	Realtime learning and control using asynchronous dynamic programmming - Baro, Bradtke, et al. - 1991
102	A reinforcement learning approach to job-shop scheduling - Zhang, Dietterich - 1995
95	Time-derivative models of pavlovian reinforcement - Sutton, Barto - 1990
94	Efficient Memory-based Learning for Robot Control. Unpublished - Moore - 1990
85	Efficient learning and planning within the dyna framework - Peng, Williams - 1993
82	Learning to control and inverted pendulum using neural networks - Anderson
75	Generalization of backpropagation with application to a recurrent gas market model, neural networks - Werbos - 1988
72	Tight performance bounds on greedy policies based on imperfect value functions - Williams, Baird - 1994
71	Active perception and reinforcement learning - Whitehead, Ballard
65	Strategy learning with multilayer connectionist representations - Anderson - 1987
64	Learning to control an unstable system with forward modeling - Jordan, Jacobs - 1990
61	Programming robots using reinforcement learning and teaching - Lin - 1991
61	Reinforcement learning with a hierarchy of abstract models - Singh - 1992
59	An upper bound on the loss from approximate optimal-value functions - Singh, Yee - 1994