allenai / allenact
An open source framework for research in Embodied-AI from AI2.
☆326Updated last month
Alternatives and similar repositories for allenact:
Users that are interested in allenact are comparing it to the libraries listed below
- ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks☆395Updated 6 months ago
- Code for the habitat challenge☆315Updated last year
- Vision-and-Language Navigation in Continuous Environments using Habitat☆344Updated last month
- A Simulation Environment to train Robots in Large Realistic Interactive Scenes☆686Updated 7 months ago
- Room-across-Room (RxR) is a large-scale, multilingual dataset for Vision-and-Language Navigation (VLN) in Matterport3D environments. It c…☆128Updated last year
- ☆328Updated 4 months ago
- Reading list for research topics in embodied vision☆565Updated this week
- Official repository of ICLR 2022 paper FILM: Following Instructions in Language with Modular Methods☆118Updated last year
- DrQ-v2: Improved Data-Augmented Reinforcement Learning☆374Updated 2 years ago
- Official codebase for EmbCLIP☆117Updated last year
- Pre-training Reusable Representations for Robotic Manipulation Using Diverse Human Video Data☆314Updated last year
- 🔀 Visual Room Rearrangement☆106Updated last year
- CLIPort: What and Where Pathways for Robotic Manipulation☆476Updated last year
- Masked Visual Pre-training for Robotics☆228Updated last year
- RoboTHOR Challenge☆85Updated 3 years ago
- A large-scale benchmark and learning environment.☆1,274Updated 3 weeks ago
- The repository for the largest and most comprehensive empirical study of visual foundation models for Embodied AI (EAI).☆474Updated 9 months ago
- Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.☆590Updated 6 months ago
- Voltron: Language-Driven Representation Learning for Robotics☆217Updated last year
- API to run VirtualHome, a Multi-Agent Household Simulator☆509Updated 3 months ago
- [ICML 2020] PyTorch Code for "One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control"☆225Updated 2 years ago
- Official implementation of "Accelerating Reinforcement Learning with Learned Skill Priors", Pertsch et al., CoRL 2020☆200Updated 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…☆90Updated last year
- Code for the paper Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration☆93Updated 2 years ago
- Utility functions when working with Ai2-THOR. Try to do one thing once.☆45Updated 2 years ago
- Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"☆267Updated 2 years ago
- Robotics Gym Environments☆410Updated last year
- Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation☆385Updated 9 months ago
- TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.☆136Updated 9 months ago
- CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks☆469Updated last month