473 search results - page 28 / 95 » Programmable Reinforcement Learning Agents |
ICML
2006
IEEE
14 years 9 months ago
2006
IEEE
We introduce the use of learned shaping rewards in reinforcement learning tasks, where an agent uses prior experience on a sequence of tasks to learn a portable predictor that est...
JMLR
2002
13 years 8 months ago
2002
Lyapunov design methods are used widely in control engineering to design controllers that achieve qualitative objectives, such as stabilizing a system or maintaining a system'...
AAAI
1993
13 years 10 months ago
1993
This paper analyzes the complexity of on-line reinforcement learning algorithms, namely asynchronous realtime versions of Q-learning and value-iteration, applied to the problem of...
AAAI
2007
13 years 11 months ago
2007
An Unobservable MDP (UMDP) is a POMDP in which there are no observations. An Only-Costly-Observable MDP (OCOMDP) is a POMDP which extends an UMDP by allowing a particular costly a...
AAAI
1998
13 years 10 months ago
1998
Learning on real robots in an real, unaltered environment provides an extremely challenging problem. Many of the simplifying assumptions made in other areas of learning cannot be ...