Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds.
Hao LiangZhi-Quan LuoPublished in: CoRR (2022)
Keyphrases
- risk sensitive
- reinforcement learning
- model free
- optimal control
- markov decision processes
- regret bounds
- control policies
- markov decision problems
- reinforcement learning algorithms
- function approximation
- optimal policy
- temporal difference
- utility function
- online learning
- dynamic programming
- state space
- action space
- policy iteration
- lower bound
- learning algorithm
- control strategies
- finite state
- upper bound
- function approximators
- control strategy
- optimality criterion
- reward function
- partially observable
- infinite horizon
- average reward
- active learning