24 search results - page 4 / 5 » Reducing reinforcement learning to KWIK online regression |
ATAL
2008
Springer
13 years 7 months ago
2008
Springer
Decentralized Markov decision processes are frequently used to model cooperative multi-agent systems. In this paper, we identify a subclass of general DEC-MDPs that features regul...
NIPS
2007
13 years 7 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...
ECML
2006
Springer
13 years 9 months ago
2006
Springer
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...
SIGIR
2008
ACM
13 years 5 months ago
2008
ACM
Relevance feedback, which traditionally uses the terms in the relevant documents to enrich the user's initial query, is an effective method for improving retrieval performanc...
AIS
2006
Springer
13 years 5 months ago
2006
Springer
The regulative and semantic `distance' of electronic conferencing may impede the topical alignment and the unambiguous interpretation of messages, hindering collaborative lear...