PAC Reinforcement Learning for Predictive State Representations.
Wenhao ZhanMasatoshi UeharaWen SunJason D. LeePublished in: CoRR (2022)
Keyphrases
- predictive state representations
- reinforcement learning
- temporal difference
- dynamical systems
- function approximation
- partially observable markov decision processes
- stochastic systems
- model free
- evaluation function
- state space
- partially observable
- past observations
- action selection
- learning algorithm
- monte carlo
- markov decision processes
- sample size
- optimal policy
- supervised learning
- multi agent
- transfer learning
- markov decision process
- policy iteration
- hidden markov models