understanding-search / maze-dataset
maze datasets for investigating OOD behavior of ML systems
☆14Updated last week
Related projects: ⓘ
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆24Updated 3 weeks ago
- PyTorch Package For Quasimetric Learning☆38Updated last year
- ☆52Updated 8 months ago
- ☆15Updated 2 years ago
- ☆39Updated 3 months ago
- ☆24Updated 2 weeks ago
- ☆20Updated last year
- Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"☆20Updated 2 months ago
- ☆65Updated 2 months ago
- Implements the Messenger environment and EMMA model.☆22Updated last year
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆26Updated last month
- JAX implementation of VQVAE/VQGAN autoencoders (+FSQ)☆19Updated 3 months ago
- We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effe…☆17Updated 7 months ago
- Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"☆30Updated 11 months ago
- ☆56Updated 2 months ago
- Source codes for the paper "COMBO: Compositional World Models for Embodied Multi-Agent Cooperation"☆25Updated 5 months ago
- Galactic Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second☆81Updated last year
- ☆28Updated 11 months ago
- ☆23Updated 10 months ago
- A lightweight research framework☆20Updated 6 months ago
- Codebase for PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem☆14Updated 2 months ago
- Interpreting how transformers simulate agents performing RL tasks☆62Updated 10 months ago
- Code for Powderworld: A Platform for Understanding Generalization via Rich Task Distributions☆63Updated 2 weeks ago
- Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.☆17Updated 3 years ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆73Updated 2 months ago
- GPT implementation in Flax☆18Updated 2 years ago
- ☆14Updated 2 weeks ago
- (NeurIPS 2023) Residual Q-Learning: Offline and Online Policy Customization without Value☆27Updated 5 months ago
- A reinforcement learning environment for the IGLU 2022 at NeurIPS☆32Updated last year
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆51Updated 5 months ago