GPU Parallelization of Policy Iteration RRT#.
R. Connor LawsonLinda WillsPanagiotis TsiotrasPublished in: CoRR (2020)
Keyphrases
- policy iteration
- markov decision processes
- parallel processing
- model free
- fixed point
- reinforcement learning
- optimal policy
- least squares
- sample path
- finite state
- markov decision process
- temporal difference
- average reward
- policy evaluation
- real time
- convergence rate
- optimal control
- state space
- infinite horizon
- parallel implementation
- graphics processing units
- linear programming
- markov decision problems
- function approximation
- markov chain
- shared memory
- dynamic programming
- long run
- machine learning
- neural network