Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/akshilpatel/centrality-experiments

Experiments for my MSc project in Hierarchical Reinforcement Learning

https://github.com/akshilpatel/centrality-experiments

Science Score: 26.0%

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

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Experiments for my MSc project in Hierarchical Reinforcement Learning

Basic Info
  • Host: GitHub
  • Owner: akshilpatel
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 492 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 7 years ago · Last pushed over 3 years ago
Metadata Files
Readme License

README.md

Graph Centrality for Option Discovery

This repository contains experiments comparing graph centrality metrics used for in subgoal detection in hierarchical reinforcement learning. I have implemented functionality for:

  • [x] State transition graph generation for a given environment (assuming discrete state and action spaces).
  • [x] Subgoal detection using node centrality metric
  • [x] Visualising the state transition graph and detected subgoals.
  • [x] Option generation given a subgoal.
  • [x] A pipeline for generating subgoals, creating options based on those subgoals, and training an agent equipped with those options.

Centrality Measures Implemented

  • [x] Betweenness
  • [x] Load
  • [x] Degree
  • [x] Closeness
  • [x] Katz
  • [x] Eigenvector
  • [x] PageRank

Setup

We build on the code from BaRLSimpleOptions. Running the experiments, therefore, requires installing BaRLSimpleOptions which can be found here, as well as networkx, numpy and pickle.

Running

To run the experiments navigate to experiments/ and run run_agent.py. This will generate options for each centrality metric and run training for an agents using each set of options generated. The results will be pickled and stored in experiments/results/. The code in experiments/results/make_graph.py can be used to generate figures displaying the results.

Owner

  • Name: Akshil Patel
  • Login: akshilpatel
  • Kind: user

PhD candidate at University of Bath working on Intrinsically Motivated and Hierarchical Reinforcement Learning.

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: 8 minutes
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • akshilpatel (1)
Top Labels
Issue Labels
Pull Request Labels