https://github.com/jeremiegince/mixture_models_deep_rl

Mixture models in deep reinforcement learning with gym
https://github.com/jeremiegince/mixture_models_deep_rl

atari deep-learning deep-neural-networks deep-reinforcement-learning gym-environment mixture-model mixture-models reinforcement-learning

Last synced: 21 days ago
JSON representation

Mixture models in deep reinforcement learning with gym

• Host: GitHub
• URL: https://github.com/jeremiegince/mixture_models_deep_rl
• Owner: JeremieGince
• Created: 2020-10-27T22:16:36.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2020-12-18T03:28:49.000Z (about 4 years ago)
• Last Synced: 2024-11-19T12:14:34.780Z (3 months ago)
• Topics: atari, deep-learning, deep-neural-networks, deep-reinforcement-learning, gym-environment, mixture-model, mixture-models, reinforcement-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 19.9 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Mixture_models_Deep_RL

1- Train all models(5) on LunarLander, Acrobot and CartPole: main_training_individual_model.py  

2- Evaluate each model on each environment: evaluate_models.py

3- Evaluate Average_ensemble method: evaluate_average_ensemble.py

4- Train Attn_ensemble: train_attn_ensemble.py

5- Evaluate Attn_ensemble: evaluate_attn_ensemble.py