Entropic Risk Optimization in Discounted MDPs.
Jia Lin HauMarek PetrikMohammad GhavamzadehPublished in: AISTATS (2023)
Keyphrases
- markov decision processes
- finite horizon
- optimal policy
- finite state
- average cost
- global optimization
- dynamic programming
- state space
- average reward
- factored mdps
- reinforcement learning
- optimization process
- optimization algorithm
- infinite horizon
- policy iteration
- markov decision process
- risk management
- information theory
- optimization problems
- risk assessment
- optimization method
- stochastic approximation
- dynamical systems
- evolutionary algorithm