114 search results - page 1 / 23 » Temporal Difference Updating without a Learning Rate |
49
Voted
NIPS
2007
15 years 2 months ago
2007
123
Voted
ISDA
2009
IEEE
15 years 7 months ago
2009
IEEE
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
100
Voted
COLT
2000
Springer
15 years 5 months ago
2000
Springer
We give the first rigorous upper bounds on the error of temporal difference (td) algorithms for policy evaluation as a function of the amount of experience. These upper bounds pr...
107
click to vote
ML
2002
ACM
15 years 23 days ago
2002
ACM
TD() is a popular family of algorithms for approximate policy evaluation in large MDPs. TD() works by incrementally updating the value function after each observed transition. It h...
120
Voted
ICML
2010
IEEE
14 years 11 months ago
2010
IEEE
Temporal difference (TD) algorithms are attractive for reinforcement learning due to their ease-of-implementation and use of "bootstrapped" return estimates to make effi...