4544 search results - page 35 / 909 » Reinforcement Learning with Time |
NIPS
1997
14 years 11 months ago
1997
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
LAMAS
2005
Springer
15 years 3 months ago
2005
Springer
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a r...
127
Voted
EWRL
2008
14 years 11 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...
GECCO
2004
Springer
15 years 3 months ago
2004
Springer
This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechani...
ML
2011
ACM
14 years 16 days ago
2011
ACM
