benbogin / obverter
Compositional Obverter Communication Learning From Raw Visual Input - Pytorch Implementation
☆19Updated 3 years ago
Alternatives and similar repositories for obverter:
Users that are interested in obverter are comparing it to the libraries listed below
- Pytorch implementation of the paper 'Compositional language emerge in a neural iterated learning' (ICLR 2020).☆14Updated 3 years ago
- Measuring compositionality in representation learning☆73Updated 6 years ago
- Learning with latent language☆51Updated 4 years ago
- ☆39Updated 9 months ago
- Automatically Composing Representation Transformations as a Means for Generalization☆24Updated 5 years ago
- Reproducing the reinforcement learning models used in "Emergence of Linguistic Communication from Referential Games with Symbolic and Pix…☆12Updated 6 years ago
- On the pitfalls of measuring emergent communication☆34Updated 6 years ago
- Grounded SCAN data set.☆69Updated 3 years ago
- PyTorch implementation for The Scattering Compositional Learner (SCL)☆32Updated 4 years ago
- Code for "Recurrent Independent Mechanisms"☆118Updated 3 years ago
- Code repository for On the interaction between supervision and self-play in emergent communication (ICLR 2020)☆16Updated 5 years ago
- This framework provides out-of-the-box implementations of Referential Games variants in order to study the emergence of artificial langua…☆22Updated last month
- ☆54Updated 3 years ago
- Annotated bibliographies.☆40Updated 5 years ago
- This repository contains code for the method and experiments of the paper "Learning with AMIGo: Adversarially Motivated Intrinsic Goals".☆61Updated last year
- Code for "Systematic Generalization: What Is Required and Can It Be Learned"☆37Updated 6 years ago
- A framework for experimenting with never-ending learning☆77Updated 6 months ago
- ☆60Updated 4 years ago
- Code for 'The Grand Atari Challenge dataset' paper☆52Updated 7 years ago
- ☆43Updated 8 years ago
- Experiment code for the ICLR 2020 paper "RTFM: Generalising to New Environment Dynamics via Reading".