Refined Regret for Adversarial MDPs with Linear Function Approximation.
Yan DaiHaipeng LuoChen-Yu WeiJulian ZimmertPublished in: ICML (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- markov decision processes
- temporal difference
- policy evaluation
- temporal difference learning
- reward function
- reinforcement learning problems
- reinforcement learning algorithms
- multi agent
- learning tasks
- model free
- state space
- radial basis function
- optimal policy
- markov decision problems
- policy search
- policy iteration
- optimal control
- dynamic programming
- pattern recognition
- partially observable
- support vector
- average reward