Keyphrases
- optimal policy
- markov decision processes
- markov decision process
- reinforcement learning
- markov decision problems
- finite horizon
- policy iteration
- discounted reward
- reward function
- policy search
- upper bound
- lower bound
- average cost
- state and action spaces
- asymptotically optimal
- state space
- average reward
- infinite horizon
- partially observable
- reinforcement learning problems
- continuous state spaces
- decision problems
- factored mdps
- worst case
- lower and upper bounds
- least squares
- policy evaluation
- decision processes
- significant improvement
- planning under uncertainty
- long run
- state dependent
- decision theoretic planning
- action space
- utility function
- upper and lower bounds