11 search results - page 1 / 3 » Reinforcement Learning Via Practice and Critique Advice |
AAAI
2010
14 years 19 days ago
2010
We consider the problem of incorporating end-user advice into reinforcement learning (RL). In our setting, the learner alternates between practicing, where learning is based on ac...
KCAP
2005
ACM
14 years 4 months ago
2005
ACM
We present a framework for knowledge transfer from one reinforcement learning task to a related task through advicetaking mechanisms. We discuss the importance of transfer in comp...
ECML
2006
Springer
14 years 2 months ago
2006
Springer
We describe a reinforcement learning system that transfers skills from a previously learned source task to a related target task. The system uses inductive logic programming to ana...
AAAI
2010
14 years 19 days ago
2010
This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian...
ATAL
2005
Springer
14 years 4 months ago
2005
Springer
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...