Awesome GitHub RepositoriesPolicy Gradient Methods

This repository provides a comprehensive library of reinforcement learning algorithms designed for training autonomous agents. It serves as a research-oriented collection of implementations that cover fundamental decision-making strategies, including dynamic programming, temporal difference learning, and policy gradient methods. The project distinguishes itself by offering specialized frameworks for deep reinforcement learning and structured decision modeling. It includes implementations for deep Q-learning that utilize neural networks, experience replay, and prioritized sampling to approxima

WebAgent is an autonomous web navigation agent and research system designed to browse the internet and synthesize information to answer complex queries. It functions as a reasoning orchestrator that navigates the web iteratively to perform deep research and extract structured data. The project includes a reinforcement learning training pipeline that generates synthetic interaction datasets for model pre-training and fine-tuning. It employs token-level policy gradients to stabilize training in non-stationary environments and uses a dual-mode inference scaling mechanism to balance execution bet

Baselines is a comprehensive suite of frameworks for reinforcement learning algorithm implementation, imitation learning, and training orchestration. It provides a library of standardized learning algorithms used to benchmark and replicate research results, alongside a deep learning policy framework for constructing neural network architectures such as multi-layer perceptrons, convolutional networks, and long short-term memory networks. The project includes a specialized imitation learning toolkit that enables agents to mimic expert behavior through behavior cloning and generative adversarial

This project is an educational repository of reinforcement learning agents and tutorials implemented using TensorFlow. It provides a practical codebase for both model-free and model-based learning agents, designed to demonstrate how AI agents learn through trial and error. The collection features detailed implementations of various algorithmic approaches, including Deep Q-Networks and Policy Gradient methods. It specifically covers Actor-Critic architectures for continuous and discrete action spaces, alongside Proximal Policy Optimization and Deep Deterministic Policy Gradients. The framewor

CleanRL is a reinforcement learning library and PyTorch framework providing a suite of reproducible implementations for online reinforcement learning algorithms. It serves as a deep reinforcement learning benchmark suite and experiment orchestrator designed for research and agent development across both discrete and continuous action spaces. The project is distinguished by its single-file algorithm implementation approach, which encapsulates each algorithm in a standalone script to eliminate complex class hierarchies. This structure is paired with a system for scheduling and executing large-s

Practical_RL is a comprehensive educational curriculum and course for learning to design and implement agents that solve complex decision processes. It provides a structured study program covering the fundamentals of reinforcement learning, from basic trial-and-error behavior to advanced deep reinforcement learning. The project includes specialized guides and frameworks for imitation learning based on expert demonstrations, model-based reinforcement learning using planners, and the training of recurrent neural networks to solve partially observed environments. The materials cover a broad ran

rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T

OpenClaw-RL is a reinforcement learning framework for training large language model agents. It provides a system for optimizing agent policies using natural language instructions, reward-based optimization, and a pipeline for refining model behavior through human or judge feedback. The framework utilizes low-rank adaptation to update model weights efficiently without full parameter tuning. It features a local-first infrastructure that allows the policy model, judge, and trainer to run on private hardware to maintain data locality. The system covers a range of optimization capabilities, inclu

本项目是一个深度强化学习课程，提供用于掌握基于神经网络的代理的教育材料与实现练习。它作为一个框架，用于构建基于价值与基于策略的方法的参考版本，以解决序列决策问题。 该项目为连续控制模拟与多智能体强化学习提供了具体实现，其中代理被训练在共享环境中合作或竞争。它包含一个用于通过 REINFORCE 等方法优化代理行为的策略梯度框架。 能力涵盖了广泛的优化算法，包括深度 Q 学习、确定性策略梯度以及用于马尔可夫决策过程（MDP）建模的动态规划。该系统支持各种训练领域，如机器人导航、金融交易自动化与基于物理的模拟。 材料以一系列 Jupyter Notebooks 的形式交付。

该项目是一个用 Python 编写的强化学习实现和教育资料集合。它提供了用于通过深度强化学习解决控制任务的神经网络架构，涵盖了基于价值（value-based）和策略梯度（policy-gradient）的方法。 该仓库包含一个进化策略和遗传算法库，作为基于梯度学习的替代方案。它还具有一个基于模型的系统，用于预测未来的环境状态和奖励，以实现内部模拟和离线规划。 该代码库涵盖了广泛的能力，包括用于稳定行为更新的 Actor-Critic 框架和近端策略优化（PPO）。它实现了诸如深度 Q 网络（DQN）、SARSA 变体和对偶网络架构等基于价值的学习技术，以及用于动作选择和基于噪声的探索机制。 该项目结构为课程，结合 Python 代码和讲座来教授深度强化学习和神经网络训练。

DRL is a curated educational resource that teaches deep reinforcement learning through a structured series of lectures and videos. It covers the three main families of reinforcement learning methods: actor-critic architectures, value-based algorithms like Q-learning and DQN, and policy-based techniques that directly optimize an agent's action-selection strategy. The curriculum extends beyond these core topics to include imitation learning, multi-agent training, and methods for handling continuous action spaces. Content is organized as markdown-driven documentation that generates static, navig

这是一个 PyTorch 强化学习库，专为在模拟环境中训练智能体而设计。它提供了一系列深度强化学习算法，重点关注策略梯度方法和信赖域优化。 该库实现了一套策略梯度算法，包括 A2C 和 PPO，以及一个使用生成对抗模仿学习 (GAIL) 的模仿学习框架。它特别具有 ACKTR 算法的可扩展实现，利用 Kronecker 因子近似来实现高效的信赖域优化。 该代码库涵盖了更广泛的功能，包括用于模拟集成的标准化环境接口、基于经验的批处理，以及用于可视化智能体行为和训练进度的工具。

OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language models as agents. It serves as an agentic reasoning optimizer and reward model trainer, providing the infrastructure to improve model decision-making through reward-based policy optimization. The project distinguishes itself through a distributed architecture that supports parameter sharding across multiple compute nodes and a coordinated rollout system for collecting interaction trajectories. It incorporates advanced reasoning strategies, such as Tree-of-Thoughts and Monte Ca

This project serves as an educational resource and training framework for developing intelligent agents through deep reinforcement learning. It provides a collection of practical tutorials and code examples designed to teach the implementation of neural networks for solving complex decision-making tasks. By focusing on hands-on learning, the material guides users through the process of building autonomous systems that improve their performance through trial and error. The framework centers on the integration of standardized simulation environments, allowing agents to interact with diverse tas

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface