17 search results - page 3 / 4 » APRICODD: Approximate Policy Construction Using Decision Dia... |
106
Voted
IJCAI
2007
15 years 2 months ago
2007
Agents often have to construct plans that obey deadlines or, more generally, resource limits for real-valued resources whose consumption can only be characterized by probability d...
CDC
2008
IEEE
15 years 7 months ago
2008
IEEE
ate Abstractions of Discrete-Time Controlled Stochastic Hybrid Systems Alessandro D’Innocenzo, Alessandro Abate, and Maria D. Di Benedetto — This work proposes a procedure to c...
90
Voted
ATAL
2009
Springer
15 years 7 months ago
2009
Springer
Reinforcement learning algorithms that use eligibility traces, such as Sarsa(λ), have been empirically shown to be effective in learning good estimated-state-based policies in pa...
135
Voted
WIOPT
2011
IEEE
14 years 4 months ago
2011
IEEE
Abstract—This paper considers maximizing throughput utility in a multi-user network with partially observable Markov ON/OFF channels. Instantaneous channel states are never known...
129
click to vote
RSS
2007
15 years 2 months ago
2007
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...