allenai / ScienceWorld
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
☆220Updated last month
Related projects ⓘ
Alternatives and complementary repositories for ScienceWorld
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆121Updated 7 months ago
- An extensible benchmark for evaluating large language models on planning☆293Updated 6 months ago
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆255Updated last year
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆279Updated 3 weeks ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆195Updated 2 weeks ago
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆220Updated 2 months ago
- Reasoning with Language Model is Planning with World Model☆145Updated last year
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆108Updated 7 months ago
- ☆137Updated 6 months ago
- ☆73Updated 4 months ago
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning☆367Updated this week
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking☆252Updated 4 months ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆86Updated last year
- AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback☆96Updated last year
- Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)☆165Updated this week
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆219Updated 5 months ago
- [NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents☆276Updated 2 months ago
- DialOp: Decision-oriented dialogue environments for collaborative language agents☆101Updated this week
- ☆198Updated last year
- ☆122Updated 2 weeks ago
- A benchmark for evaluating learning agents based on just language feedback☆58Updated last month
- [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898☆194Updated 6 months ago
- [NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling bett…☆192Updated this week
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆110Updated 3 weeks ago
- [ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"☆225Updated 3 weeks ago
- The source code of the paper "Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Pla…☆77Updated 3 months ago
- Self-Alignment with Principle-Following Reward Models☆147Updated 8 months ago
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆97Updated last month
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆365Updated last year
- Code for Arxiv 2023: Improving Language Model Negociation with Self-Play and In-Context Learning from AI Feedback☆201Updated last year