Inverse Risk-Sensitive Reinforcement Learning.
Lillian J. RatliffEric MazumdarPublished in: IEEE Trans. Autom. Control. (2020)
Keyphrases
- risk sensitive
- reinforcement learning
- model free
- optimal control
- markov decision processes
- control policies
- reinforcement learning algorithms
- function approximation
- markov decision problems
- state space
- optimal policy
- dynamic programming
- action space
- markov decision chains
- policy iteration
- temporal difference
- utility function
- average cost
- infinite horizon
- decision theoretic
- finite state
- learning algorithm
- control strategies
- control policy
- supervised learning
- action selection
- partially observable
- markov decision process
- decision processes
- average reward