17 search results - page 1 / 4 » Fast gradient-descent methods for temporal-difference learni... |
ICML
2001
IEEE
14 years 6 months ago
2001
IEEE
We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...
NIPS
2007
13 years 6 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
CORR
2010
Springer
13 years 3 months ago
2010
Springer
We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications...
ICML
2009
IEEE
14 years 6 months ago
2009
IEEE
We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and in particular the Least-Squares Temporal Difference (L...
ICML
1995
IEEE
14 years 6 months ago
1995
IEEE
A number of reinforcement learning algorithms have been developed that are guaranteed to converge to the optimal solution when used with lookup tables. It is shown, however, that ...