Keyphrases
- risk sensitive
- reinforcement learning
- model free
- markov decision processes
- optimal control
- control policies
- markov decision problems
- reinforcement learning algorithms
- function approximation
- optimal policy
- dynamic programming
- utility function
- policy iteration
- state space
- infinite horizon
- markov decision chains
- finite state
- machine learning
- action space
- supervised learning
- markov decision process
- average cost
- reward function
- temporal difference
- decision processes
- learning algorithm
- control strategy
- decision problems
- partially observable
- control strategies
- average reward
- evolutionary algorithm
- multi agent
- optimality criterion
- efficient optimization