Risk-Sensitive Reinforcement Learning via Policy Gradient Search.
Prashanth L. A.Michael C. FuPublished in: Found. Trends Mach. Learn. (2022)
Keyphrases
- policy gradient
- risk sensitive
- reinforcement learning
- optimal control
- model free
- markov decision processes
- reinforcement learning algorithms
- function approximation
- search algorithm
- search space
- utility function
- average reward
- state space
- control policies
- gradient method
- multi agent
- markov decision problems
- reinforcement learning methods
- rl algorithms
- learning algorithm
- action selection
- control strategies
- machine learning
- infinite horizon