250 search results - page 35 / 50 » Learning action effects in partially observable domains |
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
We examine the problem of evaluating a policy in the contextual bandit setting using only observations collected during the execution of another policy. We show that policy evalua...
87
Voted
ICML
2006
IEEE
15 years 10 months ago
2006
IEEE
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
AR
2007
14 years 9 months ago
2007
—Reinforcement learning is the scheme for unsupervised learning in which robots are expected to acquire behavior skills through self-explorations based on reward signals. There a...
IJRR
2008
14 years 9 months ago
2008
Designing distributed controllers for self-reconfiguring modular robots has been consistently challenging. We have developed a reinforcement learning approach which can be used bo...
ICML
2006
IEEE
15 years 10 months ago
2006
IEEE
We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal ...