60 search results - page 8 / 12 » Revisiting Natural Actor-Critics with Value Function Approxi... |
142
click to vote
AI
1998
Springer
14 years 11 months ago
1998
Springer
Reinforcement Learning (RL) is the study of programs that improve their performance by receiving rewards and punishments from the environment. Most RL methods optimize the discoun...
KI
2007
Springer
14 years 11 months ago
2007
Springer
We present an approximation method that solves a class of Decentralized hybrid Markov Decision Processes (DEC-HMDPs). These DEC-HMDPs have both discrete and continuous state variab...
ICML
2008
IEEE
16 years 15 days ago
2008
IEEE
We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the controlling agent. If these ev...
106
click to vote
PLDI
2010
ACM
15 years 4 months ago
2010
ACM
We present smooth interpretation, a method to systematically approximate numerical imperative programs by smooth mathematical functions. This approximation facilitates the use of ...
100
click to vote
UAI
2004
15 years 1 months ago
2004
Although many real-world stochastic planning problems are more naturally formulated by hybrid models with both discrete and continuous variables, current state-of-the-art methods ...