10 search results - page 1 / 2 » Policy Transfer using Reward Shaping |
ICML
2006
IEEE
14 years 11 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...
RAS
2010
13 years 9 months ago
2010
Policy Reuse is a reinforcement learning technique that efficiently learns a new policy by using past similar learned policies. The Policy Reuse learner improves its exploration b...
ICML
2003
IEEE
14 years 4 months ago
2003
IEEE
Shaping can be an effective method for improving the learning rate in reinforcement systems. Previously, shaping has been heuristically motivated and implemented. We provide a for...
ATAL
2009
Springer
14 years 5 months ago
2009
Springer
Decentralised coordination in multi-agent systems is typically achieved using communication. However, in many cases, communication is expensive to utilise because there is limited...
KCAP
2009
ACM
14 years 5 months ago
2009
ACM
As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without n...