66 search results - page 2 / 14 » Bayesian Multi-Task Reinforcement Learning |
Publication
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or ...
AGI
2011
12 years 8 months ago
2011
We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
EWRL
2008
13 years 6 months ago
2008
A wide variety of function approximation schemes have been applied to reinforcement learning. However, Bayesian filtering approaches, which have been shown efficient in other field...
IJCAI
2003
13 years 6 months ago
2003
In multiagent environments, forms of social learning such as teaching and imitation have been shown to aid the transfer of knowledge from experts to learners in reinforcement lear...
ICAART
2010
INSTICC
14 years 2 months ago
2010
INSTICC
There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most...