Stochastic Approximation for Risk-aware Markov Decision Processes.
Wenjie HuangWilliam Benjamin HaskellPublished in: CoRR (2018)
Keyphrases
- stochastic approximation
- markov decision processes
- policy iteration
- risk sensitive
- reinforcement learning
- finite state
- state space
- transition matrices
- optimal policy
- average reward
- dynamic programming
- decision theoretic planning
- temporal difference learning
- monte carlo
- fixed point
- markov decision process
- average cost
- reinforcement learning algorithms
- model free
- action space
- infinite horizon
- partially observable
- optimal control
- machine learning
- stochastic shortest path
- stochastic games
- dynamical systems
- search algorithm
- decision making