Risk-sensitive Reinforcement Learning.
Yun ShenMichael J. TobiaTobias SommerKlaus ObermayerPublished in: CoRR (2013)
Keyphrases
- risk sensitive
- reinforcement learning
- model free
- optimal control
- markov decision processes
- control policies
- reinforcement learning algorithms
- markov decision problems
- utility function
- function approximation
- state space
- markov decision chains
- optimal policy
- dynamic programming
- policy iteration
- action space
- temporal difference
- finite state
- partially observable
- decision theoretic
- control strategy
- expected utility
- average cost
- markov decision process
- machine learning
- finite horizon
- decision processes
- optimality criterion
- multi agent
- learning algorithm