473 search results - page 56 / 95 » Optimal policy switching algorithms for reinforcement learni... |
ICRA
2008
IEEE
14 years 3 months ago
2008
IEEE
— We consider the problem of optimal control in continuous and partially observable environments when the parameters of the model are not known exactly. Partially Observable Mark...
GECCO
2005
Springer
14 years 2 months ago
2005
Springer
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
AAAI
2006
13 years 10 months ago
2006
Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a ps...
ICML
1999
IEEE
14 years 9 months ago
1999
IEEE
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...
ICML
1995
IEEE
14 years 9 months ago
1995
IEEE
In this paper we introduce Ant-Q, a family of algorithms which present many similarities with Q-learning (Watkins, 1989), and which we apply to the solution of symmetric and asymm...