58 search results - page 4 / 12 » Using Learned Policies in Heuristic-Search Planning |
94
Voted
IROS
2008
IEEE
15 years 4 months ago
2008
IEEE
— A long cherished goal in artificial intelligence has been the ability to endow a robot with the capacity to learn and generalize skills from watching a human teacher. Such an ...
EWRL
2008
14 years 11 months ago
2008
We consider planning in a Markovian decision problem, i.e., the problem of finding a good policy given access to a generative model of the environment. We propose to use fitted Q-i...
90
Voted
NIPS
1993
14 years 11 months ago
1993
While exploring to nd better solutions, an agent performing online reinforcement learning (RL) can perform worse than is acceptable. In some cases, exploration might have unsafe, ...
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
IJRR
2008
14 years 9 months ago
2008
Automatically building maps from sensor data is a necessary and fundamental skill for mobile robots; as a result, considerable research attention has focused on the technical chall...