One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning.
Marc RigterBruno LacerdaNick HawesPublished in: CoRR (2022)
Keyphrases
- risk sensitive
- model free
- reinforcement learning
- markov decision processes
- optimal control
- function approximation
- reinforcement learning algorithms
- risk neutral
- markov decision chains
- temporal difference
- policy iteration
- control policies
- multi agent
- finite state
- optimal policy
- state space
- dynamic programming
- real time
- infinite horizon
- transfer learning
- markov decision process
- action space
- markov decision problems
- bayesian networks
- learning algorithm
- machine learning