5 search results - page 1 / 1 » R-MAX - A General Polynomial Time Algorithm for Near-Optimal... |
ML
2002
ACM
13 years 4 months ago
2002
ACM
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...
IJCAI
2001
13 years 6 months ago
2001
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...
ATAL
2006
Springer
13 years 8 months ago
2006
Springer
Factored representations, model-based learning, and hierarchies are well-studied techniques for improving the learning efficiency of reinforcement-learning algorithms in large-sca...
ICML
2003
IEEE
14 years 5 months ago
2003
IEEE
We present metric?? , a provably near-optimal algorithm for reinforcement learning in Markov decision processes in which there is a natural metric on the state space that allows t...
ATAL
2010
Springer
13 years 5 months ago
2010
Springer
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...