Safe Reinforcement Learning with Contrastive Risk Prediction.
Hanping ZhangYuhong GuoPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- prediction model
- multi agent
- function approximation
- prediction accuracy
- learning algorithm
- risk management
- decision making
- dynamic programming
- prediction error
- machine learning
- neural network
- high risk
- risk measures
- reinforcement learning algorithms
- temporal difference
- data sets
- markov decision processes
- supervised learning
- state space
- computational complexity
- case study
- genetic algorithm