A Probabilistic Perspective on Risk-sensitive Reinforcement Learning.
Erfaun NooraniJohn S. BarasPublished in: ACC (2022)
Keyphrases
- risk sensitive
- reinforcement learning
- model free
- optimal control
- markov decision processes
- reinforcement learning algorithms
- control policies
- markov decision problems
- function approximation
- dynamic programming
- optimal policy
- utility function
- probabilistic model
- temporal difference
- bayesian networks
- markov decision chains
- policy iteration
- optimality criterion
- state space
- learning algorithm
- expected utility
- average cost
- decision theoretic
- control strategies
- markov decision process
- action space
- decision processes
- average reward
- decision makers