Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/captaine/ppo-rnd-pommerman
Using Proximal Policy Optimization and Random Network Distillation on Pommerman
https://github.com/captaine/ppo-rnd-pommerman
bomberman ipynb proximal-policy-optimization random-network-distillation reinforcement-learning
Last synced: 3 months ago
JSON representation
Using Proximal Policy Optimization and Random Network Distillation on Pommerman
- Host: GitHub
- URL: https://github.com/captaine/ppo-rnd-pommerman
- Owner: CaptainE
- Created: 2019-03-03T15:51:48.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-03-03T16:05:32.000Z (almost 6 years ago)
- Last Synced: 2024-10-11T15:41:37.834Z (3 months ago)
- Topics: bomberman, ipynb, proximal-policy-optimization, random-network-distillation, reinforcement-learning
- Language: Jupyter Notebook
- Size: 33.2 MB
- Stars: 9
- Watchers: 2
- Forks: 1
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## PPO-RND-Pommerman
This repository contains the material used for the Pommerman project.
The methods used to get a winrate of over 50 percent over 3 simpleagents was PPO together with random network distillation.Several files can be found including:
- [Notebook with results and pre-trained model to run tests](MainResults.ipynb)
- [Notebook with code used for training](MainTraining.ipynb)
- [Python file that changes the pommerman enviornment to an input used by our model](convertInputMapToTrainingLayers.py)### Methods
**Required:**
- [Exploration by Random Network Distillation](https://arxiv.org/abs/1810.12894)
- [Proximal Policy Optimization Algorithms](https://arxiv.org/abs/1707.06347)