1166 search results - page 158 / 234 » Negotiating Using Rewards |
114
Voted
ICML
1994
IEEE
15 years 5 months ago
1994
IEEE
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
105
click to vote
EWRL
2008
15 years 4 months ago
2008
If one possesses a model of a controlled deterministic system, then from any state, one may consider the set of all possible reachable states starting from that state and using any...
119
click to vote
NIPS
2008
15 years 3 months ago
2008
Many motor skills in humanoid robotics can be learned using parametrized motor primitives as done in imitation learning. However, most interesting motor learning problems are high...
93
Voted
ANLP
1994
15 years 3 months ago
1994
Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be address...
131
Voted
ATAL
2010
Springer
15 years 2 months ago
2010
Springer
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...