Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/activeinferenceinstitute/activeblockference

https://github.com/activeinferenceinstitute/activeblockference

Science Score: 10.0%

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
  • ○
    Academic publication links
  • ✓
    Committers with academic emails
    1 of 6 committers (16.7%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.2%) to scientific vocabulary

Keywords

active active-inference cadcad inference simulation
Last synced: 5 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: ActiveInferenceInstitute
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 2.61 MB
Statistics
  • Stars: 29
  • Watchers: 10
  • Forks: 6
  • Open Issues: 0
  • Releases: 1
Topics
active active-inference cadcad inference simulation
Created about 4 years ago · Last pushed over 2 years ago
Metadata Files
Readme

README.md

💡 ActiveBlockference

This is a work-in-progress repository for active inference agents in cadCAD.

Active Blockference is an open source project that will be stewarded through deep time by the Active Inference Institute. Reduce your uncertainty about how to participate in Active Inference Institute or contact us: https://activeinference.org/

🚧 Getting Started

```

clone the repo

git clone https://github.com/ActiveInferenceInstitute/ActiveBlockference.git

cd ActiveBlockference/

create new python environment

python -m venv cad

activate the environment

source cad/bin/activate

install requirements

pip install -r requirements.txt ```

Developing Active Inference Agents in cadCAD

An active inference agent consists of the following matrices: - $A$ - the generative model's prior beliefs about how hidden states relate to observations - $B$ - the generative model's prior beliefs about controllable transitions between hidden states over time - $C$ - the biased generative model's prior preference for particular observations encoded in terms of probabilities - $D$ - the generative model's prior belief over hidden states at the first timestep

pymdp ~ Active Inference

Analysis of actinffromscratch pymdp tutorial

The pymdp inference loop has the following steps (for more information visit the official tutorial): - initialize prior to the D matrix - get observation index from grid_locations - (qs) perform inference over hidden states with `inferstates`, passing in the observation index, the A matrix, and the prior - calculate expected free energy, passing in the A, B, C matrices, the inferences (qs) from the previous step, and available actions - compute action posterior (it's the softmax of -G) - sample the action posterior the get the action - compute the prior for next state with the dot product of the B matrix (indexed with the chosen action) and the current inference (qs)

Active Gridference

The example notebook available in notebooks/ contain active inference agents moving in a grid environment with the aim of finding a preferred location.

Owner

  • Name: Active Inference Institute
  • Login: ActiveInferenceInstitute
  • Kind: user
  • Location: Online
  • Company: Active Inference Institute

http://activeinference.org/

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Committers

Last synced: about 2 years ago

All Time
  • Total Commits: 127
  • Total Committers: 6
  • Avg Commits per committer: 21.167
  • Development Distribution Score (DDS): 0.142
Past Year
  • Commits: 47
  • Committers: 1
  • Avg Commits per committer: 47.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Jakub Smékal j****l@g****m 109
C20H25N30 d****n@g****m 11
Amit Singh 4****7 3
ActiveInferenceLab 7****b 2
Pietro Monticone 3****e 1
ActiveInferenceInstitute 7****e 1

Issues and Pull Requests

Last synced: about 2 years ago

All Time
  • Total issues: 0
  • Total pull requests: 5
  • Average time to close issues: N/A
  • Average time to close pull requests: about 1 hour
  • Total issue authors: 0
  • Total pull request authors: 2
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 5
  • 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
  • smejak (4)
  • pitmonticone (1)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • cadCAD ==0.4.28
  • inferactively-pymdp ==0.0.4
  • matplotlib ==3.5.1
  • matplotlib-inline ==0.1.3
  • networkx *
  • numpy *
  • pandas *
  • plotly *
  • seaborn *