Efficient Planning in Large MDPs with Weak Linear Function Approximation.
Roshan ShariffCsaba SzepesváriPublished in: NeurIPS (2020)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- reinforcement learning problems
- markov decision processes
- model free
- planning problems
- partially observable
- temporal difference
- state space
- markov decision problems
- temporal difference learning
- radial basis function
- learning tasks
- reinforcement learning algorithms
- machine learning
- partially observable markov decision processes
- decision trees
- learning algorithm