Direct Policy Iteration with Demonstrations.
Jessica ChemaliAlessandro LazaricPublished in: IJCAI (2015)
Keyphrases
- policy iteration
- markov decision processes
- reinforcement learning
- model free
- optimal policy
- least squares
- fixed point
- sample path
- policy evaluation
- finite state
- markov decision process
- average reward
- temporal difference
- infinite horizon
- markov decision problems
- optimal control
- convergence rate
- linear programming
- average cost
- data mining