https://github.com/jianzhnie/scalerl

ScaleRL is a simple and scalable distributed reinforcement learning framework based on Python and PyTorch
https://github.com/jianzhnie/scalerl

a3c distributed-systems dppo impala parallel-computing seed-rl

Last synced: 7 months ago
JSON representation

ScaleRL is a simple and scalable distributed reinforcement learning framework based on Python and PyTorch

• Host: GitHub
• URL: https://github.com/jianzhnie/scalerl
• Owner: jianzhnie
• License: apache-2.0
• Created: 2024-10-15T06:37:13.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2024-10-30T02:28:52.000Z (11 months ago)
• Last Synced: 2024-10-30T05:01:45.943Z (11 months ago)
• Topics: a3c, distributed-systems, dppo, impala, parallel-computing, seed-rl
• Language: Python
• Homepage: https://jianzhnie.github.io/llmtech/
• Size: 221 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# ScaleRL

ScaleRL is a simple and scalable distributed reinforcement learning framework based on Python and PyTorch

### Distributed RL Libraries

- https://github.com/ray-project/ray

- https://github.com/pytorch/rl

- https://github.com/facebookresearch/torchbeast

- https://github.com/facebookresearch/rlmeta

- https://github.com/alex-petrenko/sample-factory

- https://github.com/sjtu-marl/malib.git

- https://github.com/Replicable-MARL/MARLlib

- https://github.com/seolhokim/DistributedRL-Pytorch-Ray.git

### Distributed RL Blogs

- https://www.jiqizhixin.com/articles/2024-02-15-6?from=synced&keyword=%E5%88%86%E5%B8%83%E5%BC%8F%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0

- https://joseluisc99.github.io/posts/distributed-reinforcement-learning-a-draft/

## Distributed Framework

\[1\] Massively Parallel Methods for Deep Reinforcement Learning (SGD, first distributed architecture, Gorilla DQN).

\[2\] Asynchronous Methods for Deep Reinforcement Learning (SGD, A3C).

\[3\] Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU (A3C on GPU).

\[4\] Efficient Parallel Methods for Deep Reinforcement Learning (Batched A2C, GPU).

\[5\] Evolution Strategies as a Scalable Alternative to Reinforcement Learning (ES).

\[6\] Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for

Reinforcement Learning (ES).

\[7\] RLlib: Abstractions for Distributed Reinforcement Learning (Library)

\[8\] Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes (Batched A3C).

\[9\] Distributed Prioritized Experience Replay (Ape-X, distributed replay buffer).

\[10\] IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures (CPU+GPU).

\[11\] Accelerated Methods for Deep Reinforcement Learning (Simulation Acceleration).

\[12\] GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning (Simulation Acceleration).

\[13\] DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames (DD-PPO)

\[14\] Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning (Sample Factory)

\[15\] SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference (SEED RL)