Keyphrases
- risk averse
- reinforcement learning
- markov decision processes
- reward function
- average reward
- risk neutral
- utility function
- risk aversion
- decision makers
- optimal policy
- long run
- expected utility
- stochastic programming
- state space
- portfolio management
- markov decision problems
- policy iteration
- inventory level
- risk sensitive
- markov decision process
- finite horizon
- model free
- function approximation
- average cost
- partially observable
- learning algorithm
- transition probabilities
- infinite horizon
- dynamic programming
- decision making
- probability distribution
- action space
- initial state