86 search results - page 8 / 18 » Evolution of reward functions for reinforcement learning |
ICML
2008
IEEE
16 years 14 days ago
2008
IEEE
We describe an algorithm for learning in the presence of multiple criteria. Our technique generalizes previous approaches in that it can learn optimal policies for all linear pref...
104
click to vote
GECCO
2004
Springer
15 years 5 months ago
2004
Springer
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...
ICML
2010
IEEE
15 years 22 days ago
2010
IEEE
Abstract--Reinforcement learning (RL) research typically develops algorithms for helping an RL agent best achieve its goals-however they came to be defined--while ignoring the rela...
127
click to vote
JMLR
2010
14 years 6 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
ATAL
2008
Springer
15 years 1 months ago
2008
Springer
Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...