https://github.com/adiehl96/neurosmash

A biologically plausible deep learning reinforcement agent for Neurosmash

https://github.com/adiehl96/neurosmash

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
    Found 4 DOI reference(s) in README
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

A biologically plausible deep learning reinforcement agent for Neurosmash

Basic Info
  • Host: GitHub
  • Owner: adiehl96
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 58.7 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 5 years ago · Last pushed over 5 years ago

https://github.com/adiehl96/Neurosmash/blob/main/

# Neurosmash
A plausible deep learning reinforcement agent for the Neurosmash environment.

## Deep Q-Learning Agent
Two reinforcement learning agents have been implemented. A conventional deep Q-learning agent and a biologically more plausible agent using [Hindsight Experience Replay](https://arxiv.org/abs/1707.01495). Both agents make use of the following techniques:
* Convolutional Layers
* Backpropagation
* [Frame Stacking](https://arxiv.org/abs/1312.5602)
* [LP Pooling](https://arxiv.org/abs/1204.3968)
* [Huber Loss](https://doi.org/10.1007/s00521-020-04741-w)
* [Frozen Target Network](https://arxiv.org/abs/1312.5602)

Aside from this, the vanilla implementations used
* [Memory Replay](https://doi.org/10.1109/ALLERTON.2018.8636075)

The biologically plausible agent implements 
* [Hindsight Experience Replay](https://arxiv.org/abs/1707.01495)

## Requirements
To run the program, make sure you have installed the dependencies listed in environment.yml. 
We recommend creating a conda environment for every project. You can do this with the following command:
`conda env create --file environment.yml`

## Usage
To run the networks take a look at the python notebooks in the src folder.

Owner

  • Name: Arne Diehl
  • Login: adiehl96
  • Kind: user
  • Location: Nijmegen

Master student AI @ Radboud University, machine learning enthusiast, will hopefully automate my own job away

GitHub Events

Total
Last Year