Selecting Near-Optimal Approximate State Representations in Reinforcement Learning.
Ronald OrtnerOdalric-Ambrym MaillardDaniil RyabkoPublished in: CoRR (2014)
Keyphrases
- reinforcement learning
- policy evaluation
- function approximation
- model free
- learning algorithm
- robotic control
- reinforcement learning algorithms
- selection algorithm
- relational reinforcement learning
- dynamic programming
- multi agent reinforcement learning
- temporal difference
- control problems
- provably near optimal
- least squares
- machine learning
- social networks
- temporal difference learning
- bayesian networks
- multi agent
- exact solution
- search algorithm
- markov decision processes
- dynamical systems
- optimal policy