microsoft / SmartPlayLinks
SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. SmartPlay is designed to be easy to use, and to support future development of LLMs.
☆144Updated last year
Alternatives and similar repositories for SmartPlay
Users that are interested in SmartPlay are comparing it to the libraries listed below
Sorting:
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆289Updated 2 years ago
- ☆108Updated last year
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆321Updated 3 weeks ago
- AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback☆123Updated 8 months ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆243Updated 2 weeks ago
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆276Updated last month
- ☆96Updated last year
- Reasoning with Language Model is Planning with World Model☆183Updated 2 years ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆94Updated 2 years ago
- ☆144Updated last year
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆72Updated 2 years ago
- ☆220Updated 2 years ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆198Updated 8 months ago
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆414Updated 2 years ago
- Code for Contrastive Preference Learning (CPL)☆177Updated last year
- ☆65Updated 9 months ago
- A benchmark for evaluating learning agents based on just language feedback☆93Updated 6 months ago
- Official Repo of LangSuitE☆84Updated last year
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆147Updated last year
- The source code of the paper "Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Pla…☆107Updated last year
- [ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"☆287Updated 8 months ago
- An extensible benchmark for evaluating large language models on planning☆435Updated 3 months ago
- ☆133Updated last year
- [ICLR 2024 Spotlight] Text2Reward: Reward Shaping with Language Models for Reinforcement Learning☆192Updated last year
- ☆118Updated 8 months ago
- Implementation of "Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction"☆46Updated 2 years ago
- ☆108Updated last week
- CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.☆135Updated last year
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆323Updated last year
- Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)☆159Updated last year