facebookresearch / brica
Word-order biases in deep-agent emergent communication
☆11Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for brica
- Emergent communication in agents learning about object affordances☆10Updated 5 years ago
- Cooperative Learning of Disjoint Syntax and Semantics☆49Updated 5 years ago
- Natural Environment Benchmarks for Reinforcement Learning☆20Updated 5 years ago
- Analyzing Uncertainty in Neural Machine Translation☆32Updated 3 years ago
- Emergent Communication of Generalizations, NeurIPS 2021☆14Updated 3 years ago
- Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for nat…☆27Updated 4 years ago
- Measuring compositionality in representation learning☆71Updated 5 years ago
- ☆24Updated 6 years ago
- Systematic generalization test for CLEVR☆15Updated 4 years ago
- MLE-Guided Parameter Search (AAAI 2021)☆11Updated 3 years ago
- On the pitfalls of measuring emergent communication☆34Updated 5 years ago
- Code and data for paper Colorless Green Recurrent Networks Dream Hierarchically☆90Updated 3 years ago
- Learning with latent language☆50Updated 3 years ago
- CLARA: Confidence of Labels and Raters☆11Updated last year
- Implementation of Relation Network and Recurrent Relational Network using PyTorch v1.3. Original papers: (RN) https://arxiv.org/abs/1706.…☆19Updated 2 years ago
- ☆18Updated 5 years ago
- ☆11Updated 2 years ago
- ☆28Updated 2 years ago
- PyTorch code for meta seq2seq learning☆43Updated 4 years ago
- Reward Estimation for Variance Reduction in Deep Reinforcement Learning☆21Updated 6 years ago
- Dataset and documentation for paper on explaining solutions to physical reasoning tasks (ESPRIT))☆21Updated 3 years ago
- Annotated bibliographies.☆40Updated 5 years ago
- ☆22Updated 3 years ago
- ☆58Updated 3 years ago
- Python snippets☆21Updated 4 years ago
- This is a fork of the awesome Joey-NMT with Reinforcement Learning algorithms like Policy Gradient, MRT and Advantage Actor Critic.☆27Updated last year
- Reward Estimation for Variance Reduction in Deep Reinforcement Learning☆10Updated 6 years ago
- Grounded SCAN data set.☆69Updated 2 years ago
- Separating value functions across time-scales.☆17Updated 5 years ago
- Implementation of "Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs"☆77Updated 3 years ago