48 search results - page 7 / 10 » Approximate Planning in POMDPs with Macro-Actions |
NIPS
2007
14 years 11 months ago
2007
Bayesian Reinforcement Learning has generated substantial interest recently, as it provides an elegant solution to the exploration-exploitation trade-off in reinforcement learning...
85
Voted
NIPS
2007
14 years 11 months ago
2007
Planning in partially observable environments remains a challenging problem, despite significant recent advances in offline approximation techniques. A few online methods have a...
ATAL
2009
Springer
15 years 4 months ago
2009
Springer
Coordination of multiple agents under uncertainty in the decentralized POMDP model is known to be NEXP-complete, even when the agents have a joint set of goals. Nevertheless, we s...
AAAI
2007
14 years 11 months ago
2007
Planning under uncertainty involves two distinct sources of uncertainty: uncertainty about the effects of actions and uncertainty about the current state of the world. The most wi...
IJCAI
2003
14 years 10 months ago
2003
This paper introduces the Point-Based Value Iteration (PBVI) algorithm for POMDP planning. PBVI approximates an exact value iteration solution by selecting a small set of represen...