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。
☆8Updated 6 months ago
Alternatives and similar repositories for gym_super_mario:
Users that are interested in gym_super_mario are comparing it to the libraries listed below
- 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。☆41Updated last year
- 基于gym的pytorch深度强化学习(DRL)(PPO,PPG,DQN,SAC,DDPG,TD3等算法)☆93Updated last week
- 强化学习玩超级马里奥☆67Updated 2 years ago
- Enabling Mixed Opponent Strategy Script and Self-play on SMAC☆24Updated 2 months ago
- ☆39Updated last year
- Multiagent Reinforcement Learning Research Project☆193Updated 5 months ago
- Mini HoK: a novel MARL benchmark based on the popular mobile game, Honor of Kings, to address limitations in existing environments such a…☆37Updated 3 weeks ago
- We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enh…☆153Updated last year
- GitHub's code repository is all you need☆347Updated 2 years ago
- rl-papers☆47Updated 2 years ago
- 动手学强化学习代码☆52Updated last year
- ☆36Updated 9 months ago
- ☆59Updated 2 months ago
- ☆102Updated last month
- Various explorations into the game of Poker using MCTS, NFSP, and image-recognition/web-scraping☆12Updated 4 years ago
- ☆42Updated 3 years ago
- ☆80Updated last year
- 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。☆22Updated 4 years ago
- Original PyTorch implementation of PMIC from PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Colla…☆19Updated last year
- ☆199Updated last year
- ☆38Updated 11 months ago
- Reinforcement learning☆29Updated 2 weeks ago
- 2048 environment for Reinforcement Learning and DQN algorithm☆40Updated 2 years ago
- An environment based on JSBSIM aimed at one-to-one close air combat.☆9Updated this week
- D3QN 强化学习打只狼☆26Updated 3 years ago
- mcc_second_guandan☆77Updated 2 years ago
- ☆40Updated 2 years ago
- Example code for the Gym documentation☆71Updated last year
- 人工智能模型玩王者荣耀☆156Updated 6 months ago
- OpenAI团队的深度强化学习教程中文版☆27Updated 4 years ago