MicroSTM / AGENT-synthesis
Data synthesis code for "AGENT: A Benchmark for Core Psychological Reasoning"
☆22Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for AGENT-synthesis
- ☆54Updated 3 years ago
- ☆27Updated 5 years ago
- Overcooked-AI Experiment Psiturk Demo (for MTurk experiments)☆12Updated 3 years ago
- Code for the paper Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration☆89Updated 2 years ago
- Object Centric Atari games☆48Updated this week
- ☆37Updated 2 years ago
- Grounded SCAN data set.☆69Updated 2 years ago
- Physics games involving tool use for studying human physical representations and rapid trial-and-error learning☆43Updated 4 years ago
- Code for procedurally synthesizing PHASE animations☆11Updated 2 years ago
- ☆24Updated 2 years ago
- cordial-sync is a software package than can be used to reproduce the results from the paper "A Cordial Sync: Going Beyond Marginal Polici…☆37Updated 3 years ago
- Code for the paper "Symmetric Machine Theory of Mind", presented at ICML 2022.☆12Updated 2 years ago
- Change-Based Exploration Transfer☆36Updated 2 years ago
- Web application where humans can play Overcooked with AI agents.☆57Updated last year
- Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal tra…☆87Updated last year
- CLEVR-Robot: a reinforcement learning environment combining vision, language and control.☆128Updated 3 months ago
- Code for the paper Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration☆29Updated 4 years ago
- PyTorch Implementation of "Language as an Abstraction for Hierarchical Deep Reinforcement Learning" paper☆23Updated 2 years ago
- CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery☆78Updated 2 years ago
- TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.☆135Updated 6 months ago
- Evaluating long-term memory of reinforcement learning algorithms☆133Updated last year
- Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.☆19Updated 3 years ago
- Code for "World Model as a Graph: Learning Latent Landmarks for Planning" (ICML 2021 Long Presentation)☆64Updated 3 years ago
- TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.☆67Updated last year
- Learning for effective and efficient bilevel planning☆95Updated this week
- Official code for the ACL 2021 Findings paper "Yichi Zhang and Joyce Chai. Hierarchical Task Learning from Language Instructions with Uni…☆24Updated 3 years ago
- [ICCV'21] Curious Representation Learning for Embodied Intelligence☆29Updated 3 years ago
- RAD: Reinforcement Learning with Augmented Data (code for procgen experiments)☆18Updated 3 years ago
- The Implementation of "Machine Theory of Mind", ICML 2018☆21Updated 2 years ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆83Updated 9 months ago