Near32 / ReferentialGym
This framework provides out-of-the-box implementations of Referential Games variants in order to study the emergence of artificial languages using deep learning, relying on PyTorch (https://www.pytorch.org).
☆19Updated this week
Related projects ⓘ
Alternatives and complementary repositories for ReferentialGym
- Reproducing the reinforcement learning models used in "Emergence of Linguistic Communication from Referential Games with Symbolic and Pix…☆12Updated 6 years ago
- Grounded SCAN data set.☆69Updated 2 years ago
- Measuring compositionality in representation learning☆70Updated 5 years ago
- [NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"☆112Updated 4 years ago
- Automatically Composing Representation Transformations as a Means for Generalization☆24Updated 5 years ago
- Code repository for On the interaction between supervision and self-play in emergent communication (ICLR 2020)☆16Updated 4 years ago
- Modular multitask reinforcement learning with policy sketches☆105Updated 3 years ago
- Learning with latent language☆50Updated 3 years ago
- ☆54Updated 3 years ago
- CLEVR-Robot: a reinforcement learning environment combining vision, language and control.☆128Updated 3 months ago
- Experiment code for the ICLR 2020 paper "RTFM: Generalising to New Environment Dynamics via Reading".☆38Updated 3 years ago
- Annotated bibliographies.☆40Updated 5 years ago
- Pytorch implementation of the paper 'Compositional language emerge in a neural iterated learning' (ICLR 2020).☆13Updated 3 years ago
- A job launching library for docker, EC2, GCP, etc.