Cautious Reinforcement Learning via Distributional Risk in the Dual Domain.
Junyu ZhangAmrit Singh BediMengdi WangAlec KoppelPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- machine learning
- high risk
- risk factors
- function approximation
- domain specific
- partially observable domains
- risk management
- domain independent
- transfer learning
- co occurrence
- domain experts
- markov decision processes
- learning process
- multi agent
- optimal control
- decision making
- learning classifier systems
- temporal difference
- learning algorithm
- complex domains
- neural network