179 search results - page 12 / 36 » Learning Relational Navigation Policies |
124
click to vote
Publication
We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous w...
78
Voted
ATAL
2008
Springer
14 years 11 months ago
2008
Springer
The aim of transfer learning is to accelerate learning in related domains. In reinforcement learning, many different features such as a value function and a policy can be transfer...
AIPS
2008
14 years 12 months ago
2008
The current evaluation functions for heuristic planning are expensive to compute. In numerous domains these functions give good guidance on the solution, so it worths the computat...
NIPS
2001
14 years 11 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
ICML
2005
IEEE
15 years 10 months ago
2005
IEEE
Several algorithms for learning near-optimal policies in Markov Decision Processes have been analyzed and proven efficient. Empirical results have suggested that Model-based Inter...