Recurrent Replay Distributed DQN

Introduced by Kapturowski et al. in Recurrent Experience Replay in Distributed Reinforcement Learning

Building 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 Learning

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Retrieval	4	10.53%
Image Reconstruction	3	7.89%
Astronomy	3	7.89%
Reinforcement Learning (RL)	3	7.89%
Image Retrieval	2	5.26%
In-Context Learning	1	2.63%
Denoising	1	2.63%
Uncertainty Quantification	1	2.63%
Computational Efficiency	1	2.63%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Offline Reinforcement Learning Methods