Deep Conservative Policy Iteration.
Nino VieillardOlivier PietquinMatthieu GeistPublished in: AAAI (2020)
Keyphrases
- policy iteration
- markov decision processes
- model free
- fixed point
- reinforcement learning
- optimal policy
- least squares
- sample path
- temporal difference
- finite state
- markov decision process
- infinite horizon
- policy evaluation
- average reward
- convergence rate
- linear programming
- state space
- optimal control
- markov decision problems
- discounted reward
- function approximation
- belief propagation
- multi agent