Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation.
Zechu LiTao ChenZhang-Wei HongAnurag AjayPulkit AgrawalPublished in: CoRR (2023)
Keyphrases
- massively parallel
- reinforcement learning
- parallel computers
- parallel computing
- function approximation
- reinforcement learning algorithms
- high performance computing
- state space
- multi agent reinforcement learning
- parallel programming
- fine grained
- model free
- real robot
- optimal policy
- learning algorithm
- message passing interface
- multi agent
- stochastic approximation
- processing elements
- reinforcement learning methods
- markov decision processes
- function approximators
- parallel architectures
- temporal difference learning
- action selection
- parallel machines
- policy iteration
- relational reinforcement learning
- dynamic programming
- state action
- graphics processing units
- rl algorithms
- temporal difference
- shared memory
- image segmentation