548 search results - page 5 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
ICML
2006
IEEE
15 years 10 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...
NIPS
1997
14 years 10 months ago
1997
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
JAIR
2008
14 years 9 months ago
2008
Several multiagent reinforcement learning (MARL) algorithms have been proposed to optimize agents' decisions. Due to the complexity of the problem, the majority of the previo...
ATAL
2007
Springer
15 years 3 months ago
2007
Springer
Transfer learning problems are typically framed as leveraging knowledge learned on a source task to improve learning on a related, but different, target task. Current transfer met...
ICRA
2009
IEEE
15 years 4 months ago
2009
IEEE
— In the reinforcement learning literature, transfer is the capability to reuse on a new problem what has been learnt from previous experiences on similar problems. Adapting tran...