bigrl-team / gear
A distributed GPU-centric experience replay system for large AI models.
☆16Updated last year
Related projects ⓘ
Alternatives and complementary repositories for gear
- A Really Scalable RL Framework to 10k+ CPUs☆18Updated 8 months ago
- The collection of the research works about Automatic Reinforcement Learning in Microsoft Research Asia.☆48Updated last year
- ☆18Updated 5 years ago
- ☆28Updated 2 years ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆123Updated this week
- Minimal Decision Transformer Implementation written in Jax (Flax).☆17Updated 2 years ago
- RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads☆42Updated 3 years ago
- [AutoML'22] Bayesian Generational Population-based Training (BG-PBT)☆26Updated 2 years ago
- Distributed DRL by Ray and TensorFlow Tutorial.☆9Updated 4 years ago
- ☆17Updated 5 months ago
- [ICLR 2021] Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments.☆56Updated last year
- Mirror Descent Policy Optimization☆38Updated 4 years ago
- A high-performance, scalable MindSpore reinforcement learning framework.☆41Updated 4 months ago
- Plug-and-play hydra sweepers for the EA-based multifidelity method DEHB and several population-based training variations, all proven to e…☆70Updated 11 months ago
- Code of the paper: Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function☆13Updated 2 years ago
- ☆22Updated 10 months 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☆49Updated last year
- Source code for the paper "Divergence-Augmented Policy Optimization"☆37Updated 4 years ago
- ☆10Updated last year
- MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.☆45Updated 8 months ago
- Generalized Decision Transformer for Offline Hindsight Information Matching (ICLR2022)☆66Updated 2 years ago
- ICLR 2021: "Monte-Carlo Planning and Learning with Language Action Value Estimates"☆30Updated 11 months ago
- ☆29Updated last year
- Implementation of the paper "Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation"☆13Updated last month
- A2C is a special case of PPO!☆19Updated 2 years ago
- [NeurIPS 2022 Oral] The official implementation of POR in "A Policy-Guided Imitation Approach for Offline Reinforcement Learning"☆54Updated last year
- Accelerated replay buffers in JAX☆40Updated 2 years ago
- ☆36Updated last year
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆27Updated 8 months ago