Mean-variance Based Risk-sensitive Reinforcement Learning with Interpretable Attention.
Woo Kyung KimYoungseok LeeHonguk WooPublished in: ICMVA (2022)
Keyphrases
- risk sensitive
- optimal control
- reinforcement learning
- model free
- utility function
- markov decision processes
- reinforcement learning algorithms
- markov decision problems
- control policies
- dynamic programming
- optimal policy
- function approximation
- state space
- decision makers
- control strategy
- policy iteration
- machine learning
- markov decision chains
- infinite horizon
- probability distribution
- learning algorithm
- markov decision process
- temporal difference
- action space
- optimality criterion
- multi agent