bigrl-team / gearLinks
A distributed GPU-centric experience replay system for large AI models.
☆19Updated 2 years ago
Alternatives and similar repositories for gear
Users that are interested in gear are comparing it to the libraries listed below
Sorting:
- Distributed DRL by Ray and TensorFlow Tutorial.☆10Updated 5 years ago
- ☆18Updated 6 years ago
- A Really Scalable RL Framework to 10k+ CPUs☆38Updated last year
- RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads☆46Updated 4 years ago
- Representation Learning in RL☆13Updated 3 years ago
- A novel parallel UCT algorithm with linear speedup and negligible performance loss.☆123Updated 4 years ago
- [AutoML'22] Bayesian Generational Population-based Training (BG-PBT)☆29Updated 3 years ago
- Official implementation of NeurIPS22 paper “Multi-agent Dynamic Algorithm Configuration”☆26Updated 2 years ago
- PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models. ICML 2021☆56Updated 4 years ago
- Source code for the paper "Divergence-Augmented Policy Optimization"☆37Updated 6 years ago
- ICLR 2021: "Monte-Carlo Planning and Learning with Language Action Value Estimates"☆33Updated 2 years ago
- The collection of the research works about Automatic Reinforcement Learning in Microsoft Research Asia.☆59Updated 4 months ago
- An unofficial implementation for online decision transformer☆40Updated 3 years ago
- QuaRL is an open-source framework for systematically studying the effect of applying quantization to reinforcement learning algorithms.☆75Updated 2 years ago
- ☆29Updated 3 years ago
- Mirror Descent Policy Optimization☆41Updated 5 years ago
- Related papers for offline reforcement learning (we mainly focus on representation and sequence modeling and conventional offline RL)☆18Updated 3 years ago
- MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.☆49Updated last year
- Minimal Decision Transformer Implementation written in Jax (Flax).☆17Updated 3 years ago
- Plug-and-play hydra sweepers for the EA-based multifidelity method DEHB and several population-based training variations, all proven to e…☆85Updated 2 years ago
- Tracking literature and additional online resources on transformers for sequential decision making including RL and beyond.☆49Updated 2 years ago
- A high-performance, scalable MindSpore reinforcement learning framework.☆51Updated last year
- A PyTorch implementation of SEED, originally created by Google Research for TensorFlow 2.☆15Updated 5 years ago
- Implementation of ICML 2023 paper: Future-conditioned Unsupervised Pretraining for Decision Transformer☆28Updated 2 years ago
- Results reproductions & comparisons between OpenSpiel implementations, associated paper & originating works☆17Updated 4 years ago
- on-policy optimization baselines for deep reinforcement learning☆32Updated 5 years ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆118Updated last year
- Improving upon state of the art cooperative deep reinforcement learning in StarCraft II☆13Updated 6 years ago
- Official implementation of the NeurIPS 2023 paper "Discovering General Reinforcement Learning Algorithms with Adversarial Environment Des…☆33Updated last year
- Code associated with the paper **Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees**.☆28Updated 2 years ago