69 search results - page 7 / 14 » PAC-Bayesian Policy Evaluation for Reinforcement Learning |
GECCO
2006
Springer
13 years 10 months ago
2006
Springer
In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...
IJCAI
2007
13 years 8 months ago
2007
This work presents a new algorithm, called Heuristically Accelerated Minimax-Q (HAMMQ), that allows the use of heuristics to speed up the wellknown Multiagent Reinforcement Learni...
ILP
2007
Springer
14 years 26 days ago
2007
Springer
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
AAAI
2012
11 years 9 months ago
2012
Markov decision processes (MDPs) are an established framework for solving sequential decision-making problems under uncertainty. In this work, we propose a new method for batchmod...
ATAL
2008
Springer
13 years 8 months ago
2008
Springer
In reinforcement learning, least-squares temporal difference methods (e.g., LSTD and LSPI) are effective, data-efficient techniques for policy evaluation and control with linear v...