--- id: "/non-llm-neural-networks-ml-foundations/reinforcement-learning/" title: "reinforcement learning: 41 curated resources" url: "https://skillissue.dev/non-llm-neural-networks-ml-foundations/reinforcement-learning/" --- # reinforcement learning: 41 curated resources reinforcement learning [Beginner](/non-llm-neural-networks-ml-foundations/beginner/index.md) [Intermediate](/non-llm-neural-networks-ml-foundations/intermediate/index.md) [Advanced](/non-llm-neural-networks-ml-foundations/advanced/index.md) [Expert](/non-llm-neural-networks-ml-foundations/expert/index.md) 41 resources · page 1 of 2 - ### [AlphaChip (circuit_training)](/foundations/llm-fundamentals/alphachip-circuit-training/index.md) by [Google Research](https://research.google) Google Research circuit_training GitHub repo: AlphaChip framework for chip floorplanning with reinforcement learning. entity repo West en - ### [AlphaDev](/foundations/llm-fundamentals/alphadev/index.md) by [Google DeepMind](https://www.deepmind.com/) DeepMind AlphaDev GitHub repo: pseudocode and algorithms from the faster sorting algorithms paper. entity repo UK en - ### [google-deepmind/alphatensor](/foundations/llm-fundamentals/alphatensor-2/index.md) by [Google DeepMind](https://www.deepmind.com/) DeepMind AlphaTensor GitHub repo: code for discovering faster matrix multiplication algorithms with RL. entity repo UK en - ### [Awex](/foundations/llm-fundamentals/awex/index.md) by [inclusionAI](https://inclusion-ai.org) inclusionAI Awex GitHub repo: weight synchronisation between RL training and inference engines. entity repo China en - ### [DeepSeek-R1](/foundations/llm-fundamentals/deepseek-r1-technical-repository/index.md) by [DeepSeek](https://www.deepseek.com/) DeepSeek-R1 GitHub repo: model summary, evaluation and usage for DeepSeek-R1 and R1-Zero reasoning models. entity repo China zh - ### [FinRL](/foundations/llm-fundamentals/finrl/index.md) by [AI4Finance Foundation](https://ai4finance.org) FinRL GitHub repo (AI4Finance): financial reinforcement learning framework for trading. entity repo Global en - ### [Flow](/foundations/llm-fundamentals/flow/index.md) by [flow-project](https://github.com/flow-project) Flow (UC Berkeley): framework combining traffic simulation and deep RL for mixed-autonomy traffic control. entity repo US en - ### [Gymnasium](/foundations/llm-fundamentals/gymnasium/index.md) by [Farama Foundation](https://farama.org/) Gymnasium documentation: standard API and reference environments for reinforcement learning (formerly OpenAI Gym). entity org West en - ### [Mava](/foundations/llm-fundamentals/mava/index.md) by [InstaDeep Ltd](https://instadeep.com) InstaDeep Mava GitHub repo: codebase for experiments in multi-agent reinforcement learning. entity repo UK/Tunisia en - ### [MS-SWIFT](/foundations/llm-fundamentals/ms-swift/index.md) by [ModelScope](https://www.modelscope.cn/) ModelScope ms-swift GitHub repo: framework for PEFT and full fine-tuning, DPO and GRPO of 600+ LLMs. entity repo China zh - ### [OpenAI Spinning Up](/foundations/llm-fundamentals/openai-spinning-up/index.md) by [OpenAI](https://openai.com/) OpenAI Spinning Up: educational guide to deep reinforcement learning with algorithm explanations and code. entity org West en - ### [OpenRLHF](/foundations/llm-fundamentals/openrlhf/index.md) by [OpenRLHF](https://github.com/OpenRLHF) OpenRLHF GitHub repo: Ray and vLLM based framework for RLHF and agentic RL training. entity repo China en|zh - ### [OpenSpiel](/foundations/llm-fundamentals/openspiel/index.md) by [Google DeepMind](https://www.deepmind.com/) DeepMind OpenSpiel GitHub repo: environments and algorithms for reinforcement learning and search in games. entity repo West en - ### [slime](/foundations/llm-fundamentals/slime/index.md) by [THUKEG](https://huggingface.co/THUDM) THUDM slime GitHub repo: Megatron and SGLang based framework for RL post-training at scale, used for GLM. entity repo China en - ### [THUDM (Tsinghua KEG) GitHub](/foundations/llm-fundamentals/thudm-tsinghua-keg-github/index.md) by [THUKEG](https://huggingface.co/THUDM) THUDM GitHub organisation (Tsinghua KEG and Zhipu): code for ChatGLM, GLM-4, CogVLM, CogVideoX and AgentBench. entity lab China en - ### [verl](/foundations/llm-fundamentals/verl/index.md) by [verl-project](https://github.com/verl-project) verl GitHub repo (originally ByteDance): RL post-training framework used for RLVR. entity repo China en|zh - ### [verl / HybridFlow](/foundations/llm-fundamentals/verl-hybridflow/index.md) by [verl-project](https://github.com/verl-project) verl GitHub repo: HybridFlow framework for distributed RL post-training of LLMs. entity repo China; Singapore; international zh - ### [HF Deep RL Course](/foundations/llm-fundamentals/hf-deep-rl-course/index.md) by [Hugging Face](https://huggingface.co/) Hugging Face Deep Reinforcement Learning Course: free course on RL theory and practice with hands-on units. Beginner–Intermediate learning_resource course US/France en - ### [Unsloth RL / GRPO guide](/foundations/llm-fundamentals/unsloth-rl-grpo-guide/index.md) by [Unsloth AI](https://unsloth.ai/) Unsloth reinforcement learning guide: training reasoning models with GRPO, with linked tutorials and advanced RL docs. Beginner–Intermediate learning_resource guide Australia/US en - ### [AlphaGo](/foundations/llm-fundamentals/alphago/index.md) by [Google DeepMind](https://deepmind.google/) Google DeepMind AlphaGo page covering the Go-playing system, its matches and the research papers behind it. Intermediate learning_resource blog UK en - ### [AlphaStar: Mastering the real-time strategy game StarCraft II](/foundations/llm-fundamentals/alphastar-2/index.md) by [Google DeepMind](https://deepmind.google/) Google DeepMind post on AlphaStar, the reinforcement-learning system that reached Grandmaster level in StarCraft II. Intermediate learning_resource blog UK en - ### [Easy-RL / 蘑菇书](/foundations/llm-fundamentals/easy-rl/index.md) by [Datawhale](https://datawhale.cn) Datawhale Easy-RL GitHub repo: Chinese reinforcement-learning tutorial (Mushroom Book) with code. Intermediate learning_resource course China zh - ### [YSDA Practical RL](/foundations/llm-fundamentals/ysda-practical-rl/index.md) by [Yandex School of Data Analysis](https://yandexdataschool.com) YSDA Practical_RL GitHub repo: open reinforcement-learning course with notebooks and assignments from HSE and YSDA. Intermediate–Advanced learning_resource course Russia en|ru - ### [Agent57](/foundations/llm-fundamentals/agent57/index.md) by [Adrià Puigdomènech Badia et al. (Google)](https://ai.google/) arXiv paper (2020) introducing Agent57, the first agent to exceed the human baseline on all 57 Atari games. Advanced–Expert learning_resource paper UK en - ### [Faster sorting algorithms discovered using deep reinforcement learning (AlphaDev)](/foundations/llm-fundamentals/alphadev-faster-sorting/index.md) by [Daniel J. Mankowitz et al. (Google DeepMind)](https://deepmind.google/) Nature paper (2023) on AlphaDev discovering faster sorting algorithms with deep RL. Advanced–Expert learning_resource paper West en - ### [Mastering the game of Go with deep neural networks and tree search (AlphaGo)](/foundations/llm-fundamentals/alphago-nature-2016/index.md) by [David Silver et al. (DeepMind)](https://deepmind.google/) Nature paper (2016) on AlphaGo, mastering Go with deep neural networks and tree search. Advanced–Expert learning_resource paper West en - ### [Grandmaster level in StarCraft II using multi-agent reinforcement learning (AlphaStar)](/foundations/llm-fundamentals/alphastar/index.md) by [Oriol Vinyals et al. (DeepMind)](https://deepmind.google/) Nature paper (2019) on AlphaStar reaching grandmaster level in StarCraft II with multi-agent RL. Advanced–Expert learning_resource paper West en - ### [Discovering faster matrix multiplication algorithms with reinforcement learning (AlphaTensor)](/foundations/llm-fundamentals/alphatensor/index.md) by [Alhussein Fawzi et al. (Google DeepMind)](https://deepmind.google/) Nature paper (2022) on AlphaTensor discovering faster matrix multiplication algorithms with RL. Advanced–Expert learning_resource paper West en - ### [AlphaZero](/foundations/llm-fundamentals/alphazero/index.md) by [David Silver et al. (DeepMind)](https://deepmind.google/) arXiv paper (2017) introducing AlphaZero, mastering chess and shogi through self-play reinforcement learning. Advanced–Expert learning_resource paper West en - ### [DQN (Atari)](/foundations/llm-fundamentals/dqn-atari/index.md) by [Volodymyr Mnih et al. (Google DeepMind)](https://deepmind.google/) arXiv paper (2013) "Playing Atari with Deep Reinforcement Learning", introducing DQN, deep Q-learning from pixels on Atari games. Advanced–Expert learning_resource paper West en - ### [DreamerV3](/foundations/llm-fundamentals/dreamerv3/index.md) by [Danijar Hafner et al. (Google DeepMind)](https://deepmind.google/) arXiv paper (2023) introducing DreamerV3, a world-model RL agent that masters diverse domains with fixed settings. Advanced–Expert learning_resource paper West en - ### [IMPALA](/foundations/llm-fundamentals/impala/index.md) by [Lasse Espeholt et al. (Google)](https://ai.google/) arXiv paper (2018) introducing IMPALA, a scalable distributed deep RL architecture. Advanced–Expert learning_resource paper UK en [Next page](/non-llm-neural-networks-ml-foundations/reinforcement-learning/page/2/index.md) [Plain-text Markdown copy](/non-llm-neural-networks-ml-foundations/reinforcement-learning/index.md)