Hjananggch / gym_super_marioLinks
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 8 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
Sorting:
- 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。☆44Updated last year
- D3QN 强化学习打只狼☆28Updated 3 years ago
- ☆36Updated 11 months ago
- 基于gym的pytorch深度强化学习(DRL)(PPO,PPG,DQN,SAC,DDPG,TD3等算法)☆108Updated 2 months ago
- ☆20Updated 2 years ago
- 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。☆24Updated 4 years ago
- Example code for the Gym documentation☆72Updated last year
- Multiagent Reinforcement Learning Research Project☆210Updated 7 months ago
- 强化学习玩超级马里奥☆72Updated 3 years ago
- 🍄Reinforcement Learning: Super Mario Bros with dueling dqn🍄☆120Updated 2 weeks ago
- We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enh…☆157Updated last year
- ☆85Updated last year
- Reinforcement learning☆32Updated last week
- AlphaGo-Zero-Gobang 是一个基于强化学习的五子棋(Gobang)模型,主要用以了解AlphaGo Zero的运行原理的Demo,即神经网络是如何指导MCTS做出决策的,以及如何自我对弈学习。源码+教程☆99Updated last week
- ☆65Updated last year
- A Collection of Multi-Agent Reinforcement Learning (MARL) Resources☆236Updated 2 years ago
- Reinforcement learning with PyTorch, inspired by MorvanZhou, change the framework from Tensorflow to PyTorch☆296Updated 5 years ago
- python练手小游戏☆16Updated 3 years ago
- Using deep reinforcement learning to play Snake game(贪吃蛇).☆81Updated 3 years ago
- 人工智能模型玩王者荣耀☆191Updated last month
- Solve BipedalWalkerHardcore-v2 with TD3☆89Updated 2 years ago
- Douzero with ResNet and GPU support for Windows☆43Updated 3 years ago
- ☆166Updated last year
- A gobang robot based on reinforcement learning.☆147Updated 2 years ago
- 强化学习算法库,包含了目前主流的强化学习算法(Value based and Policy based)的代码,代码都经过调试并可以运行☆86Updated last year
- ☆43Updated last month
- ☆46Updated last year
- Projects from basic algorithms to MARL. Implements MADDPG/MATD3 in Predator-Prey pursuit games with PettingZoo MPE environments.☆84Updated last week
- Multi-Agent Reinforcement Learning (MARL) papers☆259Updated 2 years ago
- GitHub's code repository is all you need☆350Updated 2 years ago