Sciweavers

81 search results - page 1 / 17
» The Optimal Reward Baseline for Gradient-Based Reinforcement...
Sort
View
UAI
2001
13 years 6 months ago
The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
There exist a number of reinforcement learning algorithms which learn by climbing the gradient of expected reward. Their long-run convergence has been proved, even in partially ob...
Lex Weaver, Nigel Tao
GECCO
2004
Springer
122views Optimization» more  GECCO 2004»
13 years 10 months ago
Gradient-Based Learning Updates Improve XCS Performance in Multistep Problems
This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechani...
Martin V. Butz, David E. Goldberg, Pier Luca Lanzi
NIPS
2001
13 years 6 months ago
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...
IJCAI
2001
13 years 6 months ago
Exploiting Multiple Secondary Reinforcers in Policy Gradient Reinforcement Learning
Most formulations of Reinforcement Learning depend on a single reinforcement reward value to guide the search for the optimal policy solution. If observation of this reward is rar...
Gregory Z. Grudic, Lyle H. Ungar
ICML
2002
IEEE
14 years 5 months ago
Hierarchically Optimal Average Reward Reinforcement Learning
Two notions of optimality have been explored in previous work on hierarchical reinforcement learning (HRL): hierarchical optimality, or the optimal policy in the space defined by ...
Mohammad Ghavamzadeh, Sridhar Mahadevan