Offline Reinforcement Learning Methods
Recurrent Replay Distributed DQN
Introduced by Kapturowski et al. in Recurrent Experience Replay in Distributed Reinforcement LearningBuilding on the recent successes of distributed training of RL agents, R2D2 is an RL approach that trains a RNN-based RL agents from distributed prioritized experience replay. Using a single network architecture and fixed set of hyperparameters, Recurrent Replay Distributed DQN quadrupled the previous state of the art on Atari-57, and matches the state of the art on DMLab-30. It was the first agent to exceed human-level performance in 52 of the 57 Atari games.
Source: Recurrent Experience Replay in Distributed Reinforcement LearningPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Retrieval | 4 | 16.67% |
| Reinforcement Learning (RL) | 3 | 12.50% |
| Image Retrieval | 2 | 8.33% |
| Simultaneous Localization and Mapping | 1 | 4.17% |
| Visual Place Recognition | 1 | 4.17% |
| Meta-Learning | 1 | 4.17% |
| Systematic Generalization | 1 | 4.17% |
| Data-to-Text Generation | 1 | 4.17% |
| NER | 1 | 4.17% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
