The Role of Discount Factor in Risk Sensitive Markov Decision Processes.
Valdinei FreirePublished in: BRACIS (2016)
Keyphrases
- markov decision processes
- risk sensitive
- discount factor
- optimal policy
- markov decision problems
- state space
- dynamic programming
- reinforcement learning
- average reward
- policy iteration
- finite state
- average cost
- planning under uncertainty
- infinite horizon
- decision processes
- action space
- partially observable
- finite horizon
- decision making
- markov decision process
- reinforcement learning algorithms
- function approximation
- reward function
- linear programming
- search space
- computational complexity
- decision problems