Keyphrases
- optimal policy
- markov decision processes
- markov decision process
- markov decision problems
- finite horizon
- policy iteration
- policy search
- state space
- state and action spaces
- reinforcement learning
- average cost
- reward function
- average reward
- infinite horizon
- partially observable
- action space
- reinforcement learning problems
- finite state
- risk measures
- decision problems
- dynamic programming
- long run
- continuous state spaces
- approximate dynamic programming
- factored mdps
- linear programming
- robust optimization
- nonparametric estimation
- discounted reward
- policy evaluation
- decision processes
- control policy
- portfolio selection
- state dependent
- initial state
- decision theoretic planning
- decision theoretic
- machine learning
- image gradient
- action selection