A collection of my implemented advanced & complex RL agents for complex games like Soccer, Street Fighter III, Rubik's Cube, VizDoom, Montezuma, Kungfu-Master, super-mario-bros and more by implementing various DRL algorithms using gym, unity-ml, pygame, sb3, rl-zoo, rubiks_cube_gym and sample factory libraries. I have added some links in Acknowledgement section below.
To see my simple & intermediate agents for relatively simple environments; visit this repository: https://github.com/hishamcse/DRL-Renegades-Game-Bots
- Unity Ml Agents
- Curiosity Driven RL - Random Network Distillation(RND)
- PPO + RND
- MultiAgent Reinforcement Learning(MARL)
- Self Play
- Sample Factory
- Asynchronous Advantage Actor-Critic (A3C)
- Intrinsic Curiosity Module (ICM)
- Decision Transformer (both online & offline)
| Environments | Libraries Used(includes HF) | Algos | Kaggle Notebooks |
|---|---|---|---|
| MontezumaRevengeNoFrameskip-v4 | pytorch, gym, atari | PPO + RND(CNN) - Scratch | Link |
| Super-Mario-Bros | pytorch, gym, atari | PPO + RND(CNN) - Scratch | Link |
| SoccerTwos | unity-mlagents | MA-POCA | Link |
| VizDoom (doom_health_gathering_supreme) | sample_factory | PPO | Link |
| Doom Deathmatch (doom_deathmatch_bots) | sample_factory | APPO | Link |
| KungFuMaster-v5 | pytorch, gym | A3C-ICM-scratch | Link |
| HalfCheetah-v4 | pytorch, decision transformer | Decision Transformer | Link |
| Hopper-v4 | pytorch, decision transformer | Decision Transformer | Link |
| RubiksCube-v0 | pytorch, gym_rubiks_cube, decision transformer | Decision Transformer | Link |
| Street Fighter III | diambra, stable-baseline3 | PPO | Run locally |
| Ultimate Mortal Kombat 3 | diambra, stable-baseline3 | PPO | Run locally |
Find all my traned agents at hishamcse agents
- Deep RL Course
- Thomas Simonini
- Open RL Leaderboard - HuggingFace
- PPO-RND for Montezuma & Mario
- RND - Random Network Distillation
- CleanRL Single File Implementations
- Unity-mlagents
- gym
- Sample_Factory
- RL-Zoo3
- QRDQN - Quantile Regression DQN
- Deep RL Paradise
- OpenAI Spinning Up
- Awesome Deep RL
- Dennybritz RL
- HuggingFace Hub Python Library
- Uvipen
- Ted Deng
- Street-fighter-A3C-ICM-pytorch
- Solve-Rubiks-Cube-using-Transformer
- CubeGPT
- GymRubiksCube
- Diambra
- Diambra Doc
- Diambra Tutorial
You can view my Deep Reinforcement Learning projects