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 4 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。☆37Updated last year
- Multiagent Reinforcement Learning Research Project☆156Updated 4 months ago
- 基于gym的pytorch深度强化学习(DRL)(PPO,PPG,DQN,SAC,DDPG,TD3等算法)☆81Updated last week
- ☆58Updated last year
- We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enh…☆148Updated last year
- PyTorch implementations of MADDPG, MAPPO (coming)☆110Updated 11 months ago
- ☆73Updated last year
- A Collection of Multi-Agent Reinforcement Learning (MARL) Resources☆217Updated 2 years ago
- Exercise Solutions for Reinforcement Learning: An Introduction [2nd Edition]☆16Updated 4 years ago
- Example code for the Gym documentation☆71Updated last year
- Solve BipedalWalkerHardcore-v2 with TD3☆84Updated last year
- 多智能体强化学习（MARL）算法复现，包括QMIX，VDN，QTRAN、MAVEN等等☆186Updated 2 years ago
- notes☆27Updated 2 years ago
- ☆159Updated last year
- D3QN 强化学习打只狼☆25Updated 3 years ago
- LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmi…☆107Updated last month
- implementation of MADDPG using PyTorch and multiagent-particle-envs☆32Updated 2 years ago
- Multi-UAV target round-up based on MADDPG☆82Updated 3 months ago
- 一些有趣算法的动态演示💻 蚁群算法、A星寻路、碰撞检测……☆35Updated 2 years ago
- Multi-Agent Reinforcement Learning (MARL) papers☆232Updated 2 years ago
- ☆94Updated 3 years ago
- 2048 environment for Reinforcement Learning and DQN algorithm☆39Updated 2 years ago
- implementation of MADDPG using PettingZoo and PyTorch☆122Updated last year
- A Reinforcement Learning Project using PPO + LSTM☆59Updated last year
- gym 框架下的多智能体追逃博弈强化学习平台☆11Updated last year
- GitHub's code repository is all you need☆341Updated last year
- Multi-agent Combat Arena (UAV swarm vs UAV swarm)☆115Updated 4 years ago
- Algorithm that combines QMIX with SAC for Multi-Agent Reinforcement Learning.☆44Updated 2 years ago
- Multi-Agent Constrained Policy Optimisation (MACPO; MAPPO-L).☆159Updated 10 months ago
- 多智能体强化学习VDN、QMIX、QTRAN、QPLEX复现☆30Updated last year