458 search results - page 47 / 92 » Q-Decomposition for Reinforcement Learning Agents |
144
Voted
ATAL
2009
Springer
16 years 16 days ago
2009
Springer
We present a general methodology to automate the search for equilibrium strategies in games derived from computational experimentation. Our approach interleaves empirical game-the...
160
click to vote
ICML
2005
IEEE
16 years 6 months ago
2005
IEEE
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...
178
click to vote
ATAL
2007
Springer
16 years 4 days ago
2007
Springer
It is known that the complexity of the reinforcement learning algorithms, such as Q-learning, may be exponential in the number of environment’s states. It was shown, however, th...
179
click to vote
IJCAI
2001
15 years 7 months ago
2001
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...
148
click to vote
ECML
2004
Springer
15 years 11 months ago
2004
Springer
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....