openpsi-project / srl
A Really Scalable RL Framework to 10k+ CPUs
☆33Updated last year
Alternatives and similar repositories for srl
Users that are interested in srl are comparing it to the libraries listed below
Sorting:
- A distributed GPU-centric experience replay system for large AI models.☆18Updated last year
- A high-performance, scalable MindSpore reinforcement learning framework.☆47Updated 10 months ago
- SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores☆15Updated last year
- RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads☆43Updated 4 years ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 6 months ago
- Allow torch tensor memory to be released and resumed later☆29Updated this week
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆112Updated 8 months ago
- Uni-RLHF platform for "Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback" (ICLR2024…☆36Updated 5 months ago
- Launch programs on multiple hosts. (多机启动程序)☆14Updated last year
- ☆29Updated last year
- Distributed DRL by Ray and TensorFlow Tutorial.☆9Updated 5 years ago
- ☆18Updated 6 years ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆292Updated 3 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 10 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆78Updated 5 months ago
- ☆30Updated 2 years ago
- PyTorch implementations for Offline Preference-Based RL (PbRL) algorithms☆20Updated last month
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆18Updated last week
- ☆88Updated 2 years ago
- Distributed ML Optimizer☆32Updated 3 years ago
- Source code for the paper "Divergence-Augmented Policy Optimization"☆37Updated 5 years ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆91Updated last month
- ☆70Updated last week
- Benchmarked implementations of Offline RL Algorithms.☆72Updated 2 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆209Updated last month
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆38Updated 2 years ago
- Natural Language Reinforcement Learning☆87Updated 4 months ago
- This is the source code of Agar.io environment.☆23Updated 3 years ago
- Code accompanying the paper "TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play" (AAMAS 2023) 足球游戏智能体☆54Updated last year
- Async pipelined version of Verl☆74Updated last month