246 search results - page 2 / 50 » Learning behavior styles with inverse reinforcement learning |
103
Voted
ETS
2007
IEEE
15 years 5 months ago
2007
IEEE
162
click to vote
IJCAI
2003
15 years 7 months ago
2003
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
174
click to vote
IJCAI
2007
15 years 7 months ago
2007
Inverse Reinforcement Learning (IRL) is the problem of learning the reward function underlying a Markov Decision Process given the dynamics of the system and the behaviour of an e...
167
click to vote
ICML
2004
IEEE
16 years 6 months ago
2004
IEEE
We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we wa...