Efficient Planning in Large MDPs with Weak Linear Function Approximation.
Roshan ShariffCsaba SzepesváriPublished in: CoRR (2020)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- reinforcement learning problems
- function approximators
- markov decision processes
- temporal difference learning
- learning tasks
- temporal difference
- state space
- neural network
- reinforcement learning algorithms
- dynamic programming
- radial basis function
- markov decision problems
- temporal difference methods
- model free
- action selection
- policy gradient
- initial state
- text classification
- genetic algorithm