|
Volumn , Issue , 2005, Pages 690-695
|
Reinforcement learning in POMDPs without resets
|
Author keywords
[No Author keywords available]
|
Indexed keywords
AVERAGE REWARD;
BALANCING EXPLORATION AND EXPLOITATIONS;
BUILDING BLOCKES;
CONVERGENCE RATES;
NEAR-OPTIMAL;
OPTIMAL POLICIES;
UNKNOWN ENVIRONMENTS;
UNOBSERVABLE;
ARTIFICIAL INTELLIGENCE;
OPTIMIZATION;
REINFORCEMENT LEARNING;
ALGORITHMS;
|
EID: 84880715629
PISSN: 10450823
EISSN: None
Source Type: Conference Proceeding
DOI: None Document Type: Conference Paper |
Times cited : (33)
|
References (13)
|