Hjananggch / gym_super_mario
本项目旨在探索强化学习技术在经典游戏《超级玛丽》中的应用，通过训练一个智能代理来自主导航并完成游戏关卡。我们采用了深度Q网络（DQN）和双深度Q网络（DDQN）等先进的强化学习算法，结合神经网络，使得代理能够学习如何在游戏世界中生存并获得高分。 项目特点 强化学习实践：本项目是强化学习理论与实践的结合，展示了如何将强化学习算法应用于实际问题中。 深度学习集成：通过集成深度学习模型，我们的智能代理能够处理复杂的游戏环境并做出决策。 环境优化：我们对游戏环境进行了优化，包括状态预处理和奖励设计，以提高学习效率和代理性能。 可视化工具：项目包含了训练过程的可视化工具，帮助开发者和研究人员理解代理的学习进度和行为策略。
☆7Updated last month
Related projects ⓘ
Alternatives and complementary repositories for gym_super_mario
- 一个简洁易用3D场景创建和控制工具。基于ThreeJS。纯Python接口。它适用于科研、多智能体强化学习领域的3D演示、娱乐等应用。☆36Updated 10 months ago
- 强化学习玩超级马里奥☆55Updated 2 years ago
- 基于gym的pytorch深度强化学习(DRL)(PPO,PPG,DQN,SAC,DDPG,TD3等算法)☆64Updated 2 months ago
- ☆62Updated last year
- Multiagent Reinforcement Learning Research Project☆116Updated 3 weeks ago
- GitHub's code repository is all you need☆325Updated last year
- XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library☆641Updated last week
- ☆96Updated 4 months ago
- We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enh…☆129Updated 10 months ago
- ☆57Updated 3 weeks ago
- LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmi…☆80Updated 2 weeks ago
- ☆55Updated 10 months ago
- ☆336Updated last week
- TextStarCraft2,a pure language env which support llms play starcraft2☆209Updated 3 weeks ago
- A Collection of Multi-Agent Reinforcement Learning (MARL) Resources☆208Updated 2 years ago
- 动手学强化学习代码☆35Updated 9 months ago
- An easier PyTorch deep reinforcement learning library.☆166Updated 2 months ago
- 2024年腾讯开悟智能体比赛（王者荣耀AI比赛，稳定版）☆15Updated 2 months ago
- Reinforcement learning with PyTorch, inspired by MorvanZhou, change the framework from Tensorflow to PyTorch☆255Updated 4 years ago
- 多智能体强化学习（MARL）算法复现，包括QMIX，VDN，QTRAN、MAVEN等等☆179Updated 2 years ago
- Honor of Kings AI Open Environment of Tencent☆644Updated 3 months ago
- rl-papers☆42Updated last year
- An environment based on JSBSIM aimed at one-to-one close air combat.☆290Updated 2 weeks ago
- Lightweight version of MAPPO to help you quickly migrate to your local environment.☆498Updated last month
- 基于Pytorch实现的PPO强化学习模型，支持训练各种游戏，如超级马里奥，雪人兄弟，魂斗罗等等。☆18Updated 3 years ago
- D3QN 强化学习打只狼☆21Updated 2 years ago
- 本仓库提供了一个基于PyTorch实现的Transformer模型示例代码，专为初学者设计，用以深入浅出地讲解Transformer架构的工作原理和应用。通过阅读和运行此项目中的代码，学习者可以快速理解自注意力机制、编码器-解码器结构以及如何在实际任务中使用Transfor…☆38Updated 10 months ago
- ☆185Updated last year
- 《动手学强化学习》练习代码（Pytorch）☆11Updated 2 years ago
- A parallel framework for population-based multi-agent reinforcement learning.☆497Updated 10 months ago