Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion.
Taehyun ChoSeungyub HanHeesoo LeeKyungjae LeeJungwoo LeePublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- risk management
- risk assessment
- function approximation
- minimum description length
- markov decision processes
- learning algorithm
- dynamic programming
- risk factors
- model free
- state space
- reinforcement learning methods
- risk measures
- risk analysis
- temporal difference
- optimal policy
- reinforcement learning algorithms
- optimal control
- natural disasters
- optimization criterion
- multi agent reinforcement learning
- minimum risk
- robotic control
- temporal difference learning
- data sets
- partially observable
- high risk
- decision makers
- markov random field
- hidden markov models
- learning environment
- decision making
- feature selection
- genetic algorithm