Reinforcement Learning
41 resources · page 1 of 2
AlphaChip (circuit_training)
Creator not supplied; see original source.
Google Research circuit_training GitHub repo: AlphaChip framework for chip floorplanning with reinforcement learning.
AlphaDev
Creator not supplied; see original source.
DeepMind AlphaDev GitHub repo: pseudocode and algorithms from the faster sorting algorithms paper.
google-deepmind/alphatensor
Creator not supplied; see original source.
DeepMind AlphaTensor GitHub repo: code for discovering faster matrix multiplication algorithms with RL.
Awex
Creator not supplied; see original source.
inclusionAI Awex GitHub repo: weight synchronisation between RL training and inference engines.
DeepSeek-R1
Creator not supplied; see original source.
DeepSeek-R1 GitHub repo: model summary, evaluation and usage for DeepSeek-R1 and R1-Zero reasoning models.
FinRL
Creator not supplied; see original source.
FinRL GitHub repo (AI4Finance): financial reinforcement learning framework for trading.
Flow
Creator not supplied; see original source.
Flow (UC Berkeley): framework combining traffic simulation and deep RL for mixed-autonomy traffic control.
Gymnasium
Creator not supplied; see original source.
Gymnasium documentation: standard API and reference environments for reinforcement learning (formerly OpenAI Gym).
Mava
Creator not supplied; see original source.
InstaDeep Mava GitHub repo: codebase for experiments in multi-agent reinforcement learning.
MS-SWIFT
Creator not supplied; see original source.
ModelScope ms-swift GitHub repo: framework for PEFT and full fine-tuning, DPO and GRPO of 600+ LLMs.
OpenAI Spinning Up
Creator not supplied; see original source.
OpenAI Spinning Up: educational guide to deep reinforcement learning with algorithm explanations and code.
OpenRLHF
Creator not supplied; see original source.
OpenRLHF GitHub repo: Ray and vLLM based framework for RLHF and agentic RL training.
OpenSpiel
Creator not supplied; see original source.
DeepMind OpenSpiel GitHub repo: environments and algorithms for reinforcement learning and search in games.
slime
Creator not supplied; see original source.
THUDM slime GitHub repo: Megatron and SGLang based framework for RL post-training at scale, used for GLM.
THUDM (Tsinghua KEG) GitHub
Creator not supplied; see original source.
THUDM GitHub organisation (Tsinghua KEG and Zhipu): code for ChatGLM, GLM-4, CogVLM, CogVideoX and AgentBench.
verl
Creator not supplied; see original source.
verl GitHub repo (originally ByteDance): RL post-training framework used for RLVR.
verl / HybridFlow
Creator not supplied; see original source.
verl GitHub repo: HybridFlow framework for distributed RL post-training of LLMs.
HF Deep RL Course
Creator not supplied; see original source.
Hugging Face Deep Reinforcement Learning Course: free course on RL theory and practice with hands-on units.
Unsloth RL / GRPO guide
Creator not supplied; see original source.
Unsloth reinforcement learning guide: training reasoning models with GRPO, with linked tutorials and advanced RL docs.
AlphaGo
Creator not supplied; see original source.
Google DeepMind AlphaGo page covering the Go-playing system, its matches and the research papers behind it.
AlphaStar: Mastering the real-time strategy game StarCraft II
Creator not supplied; see original source.
Google DeepMind post on AlphaStar, the reinforcement-learning system that reached Grandmaster level in StarCraft II.
Easy-RL / 蘑菇书
Creator not supplied; see original source.
Datawhale Easy-RL GitHub repo: Chinese reinforcement-learning tutorial (Mushroom Book) with code.
YSDA Practical RL
Creator not supplied; see original source.
YSDA Practical_RL GitHub repo: open reinforcement-learning course with notebooks and assignments from HSE and YSDA.
Agent57
Creator not supplied; see original source.
arXiv paper (2020) introducing Agent57, the first agent to exceed the human baseline on all 57 Atari games.
Faster sorting algorithms discovered using deep reinforcement learning (AlphaDev)
Creator not supplied; see original source.
Nature paper (2023) on AlphaDev discovering faster sorting algorithms with deep RL.
Mastering the game of Go with deep neural networks and tree search (AlphaGo)
Creator not supplied; see original source.
Nature paper (2016) on AlphaGo, mastering Go with deep neural networks and tree search.
Grandmaster level in StarCraft II using multi-agent reinforcement learning (AlphaStar)
Creator not supplied; see original source.
Nature paper (2019) on AlphaStar reaching grandmaster level in StarCraft II with multi-agent RL.
Discovering faster matrix multiplication algorithms with reinforcement learning (AlphaTensor)
Creator not supplied; see original source.
Nature paper (2022) on AlphaTensor discovering faster matrix multiplication algorithms with RL.
AlphaZero
Creator not supplied; see original source.
arXiv paper (2017) introducing AlphaZero, mastering chess and shogi through self-play reinforcement learning.
DQN (Atari)
Creator not supplied; see original source.
arXiv paper (2013) "Playing Atari with Deep Reinforcement Learning", introducing DQN, deep Q-learning from pixels on Atari games.
DreamerV3
Creator not supplied; see original source.
arXiv paper (2023) introducing DreamerV3, a world-model RL agent that masters diverse domains with fixed settings.
IMPALA
Creator not supplied; see original source.
arXiv paper (2018) introducing IMPALA, a scalable distributed deep RL architecture.