RL training scripts for learning an agent using ProcTHOR.
☆37Feb 18, 2025Updated last year
Alternatives and similar repositories for procthor-rl
Users that are interested in procthor-rl are comparing it to the libraries listed below
Sorting:
- Unbiased Directed Object Attention Graph for Object Navigation☆15Nov 28, 2022Updated 3 years ago
- Official Repository for 'Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences' (CVPR 2024)☆16Mar 29, 2024Updated last year
- Visual Navigation with Spatial Attention☆37Jan 2, 2025Updated last year
- Python package for importing and loading external assets into AI2THOR☆31Jan 5, 2026Updated 2 months ago
- ☆27Mar 4, 2022Updated 4 years ago
- Evaluating pre-trained navigation agents under corruptions☆31Sep 7, 2021Updated 4 years ago
- Official implementation of NeurIPS 2022 paper "Learning Active Camera for Multi-Object Navigation"☆10Apr 23, 2023Updated 2 years ago
- Python implementation of the paper Learning hierarchical relationships for object-goal navigation☆48Dec 8, 2022Updated 3 years ago
- Collections of object goal navigation papers in recent top-tier conferences.☆14Sep 24, 2022Updated 3 years ago
- GMAN: Generative Meta-Adversarial Network for Unseen Object Navigation (ECCV 2022)☆23Jan 13, 2024Updated 2 years ago
- ☆30Dec 23, 2023Updated 2 years ago
- Commonsense Scene Graph-based Target Localization for Object Search☆15Apr 2, 2024Updated last year
- SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World☆148Nov 4, 2024Updated last year
- Official GitHub Repository for paper "Visual Graph Memory with Unsupervised Representation for Visual Navigation", ICCV 2021☆66Nov 24, 2025Updated 3 months ago
- The ProcTHOR-10K Houses Dataset☆119Dec 14, 2022Updated 3 years ago
- MimicLabs: A Scalable Data Collection & Generation Pipeline for Table-top Manipulation☆36Feb 6, 2026Updated last month
- Starter code and instructions for participating in MultiON Challenge 2021.☆12Jun 12, 2024Updated last year
- RoboTHOR Challenge☆97May 17, 2021Updated 4 years ago
- 🚀 Run AI2-THOR with Google Colab☆39Aug 4, 2022Updated 3 years ago
- Pushing it out of the Way: Interactive Visual Navigation☆44Jan 26, 2024Updated 2 years ago
- Code for training embodied agents using IL and RL finetuning at scale for ObjectNav☆90Apr 13, 2025Updated 10 months ago
- [CVPR 2025🔥] Official codebase for "Global-Local Tree Search in VLMs for 3D Indoor Scene Generation"☆20Apr 18, 2025Updated 10 months ago
- (CVPR 2025) A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning☆24Mar 11, 2025Updated 11 months ago
- Zeroshot Active VIsual Search☆15Jun 18, 2023Updated 2 years ago
- Aligning Knowledge Graph with Visual Perception for Object-goal Navigation (ICRA 2024)☆42Jan 8, 2026Updated 2 months ago
- The code of the paper "DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects"☆20May 2, 2025Updated 10 months ago
- [ICRA 2021] SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation☆49Mar 9, 2021Updated 4 years ago
- Resources for Auxiliary Tasks and Exploration Enable ObjectNav☆42Oct 22, 2021Updated 4 years ago
- ☆47Sep 30, 2023Updated 2 years ago
- Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation (CVPR2024)☆55Mar 27, 2025Updated 11 months ago
- ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings. NeurIPS 2022☆100Jan 31, 2023Updated 3 years ago
- 📱👉🏠 Perform conditional procedural generation to generate houses like your own!☆60Aug 11, 2023Updated 2 years ago
- ☆31Nov 6, 2024Updated last year
- ☆26Jan 12, 2025Updated last year
- Thisi is the official code base for paper "Think Before You Act: Decision Transformers with Internal Working Memory"☆23Jul 12, 2024Updated last year
- Official implementation of OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models☆59Sep 17, 2024Updated last year
- 🐍 A Python Package for Seamless Data Distribution in AI Workflows☆26Nov 30, 2023Updated 2 years ago
- Codebase for PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem☆24Jul 11, 2024Updated last year
- Use local AI within the browser☆32Updated this week