Gradient-based inverse risk-sensitive reinforcement learning.
Eric MazumdarLillian J. RatliffTanner FiezS. Shankar SastryPublished in: CDC (2017)
Keyphrases
- risk sensitive
- model free
- reinforcement learning
- optimal control
- markov decision processes
- reinforcement learning algorithms
- function approximation
- temporal difference
- markov decision problems
- control policies
- markov decision chains
- optimal policy
- state space
- utility function
- policy iteration
- dynamic programming
- control strategies
- transfer learning
- multi agent
- finite state
- learning algorithm
- decision problems
- decision processes