Epistemic Risk-Sensitive Reinforcement Learning.
Hannes ErikssonChristos DimitrakakisPublished in: ESANN (2020)
Keyphrases
- risk sensitive
- reinforcement learning
- model free
- optimal control
- markov decision processes
- control policies
- markov decision problems
- reinforcement learning algorithms
- function approximation
- utility function
- temporal difference
- optimal policy
- state space
- dynamic programming
- policy iteration
- markov decision chains
- machine learning
- finite state
- control strategy
- multi agent
- control strategies
- infinite horizon
- markov decision process
- finite horizon
- learning agent
- average reward
- transfer learning
- supervised learning