Difference between revisions of "Distributed Deep Reinforcement Learning (DDRL)"
| Line 14: | Line 14: | ||
a new, highly scalable agent architecture for distributed training called Importance Weighted Actor-Learner Architecture that uses a new off-policy correction algorithm called V-trace. | a new, highly scalable agent architecture for distributed training called Importance Weighted Actor-Learner Architecture that uses a new off-policy correction algorithm called V-trace. | ||
| − | <youtube>YMfJLFynmA</youtube> | + | <youtube>-YMfJLFynmA</youtube> |
== DMLab-30 == | == DMLab-30 == | ||
Revision as of 21:36, 15 February 2019
Youtube search... ...Google search
- IMPALA (Importance Weighted Actor-Learner Architecture)
- Importance Weighted Actor-Learner Architectures: Scalable Distributed DeepRL in DMLab-30
- Deep Reinforcement Learning (DRL)
a new, highly scalable agent architecture for distributed training called Importance Weighted Actor-Learner Architecture that uses a new off-policy correction algorithm called V-trace.
DMLab-30
Youtube search... ...Google search
DMLab-30 is a collection of new levels designed using our open source RL environment DeepMind Lab. These environments enable any DeepRL researcher to test systems on a large spectrum of interesting tasks either individually or in a multi-task setting.
