1989Ryan / llm-mcts
[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.
☆141Updated 3 months ago
Related projects: ⓘ
- [ICLR 2024] Code for the paper "Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning"☆113Updated 8 months ago
- Paper collections of the continuous effort start from World Models.☆127Updated 2 months ago
- The source code of the paper "Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Pla…☆69Updated last month
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆213Updated 3 weeks ago
- [ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"☆209Updated 3 weeks ago
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆248Updated last year
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆84Updated last year
- ☆131Updated 4 months ago
- AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback☆82Updated last year
- ☆102Updated 2 months ago
- Reasoning with Language Model is Planning with World Model☆137Updated last year
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆115Updated 5 months ago
- Code for Contrastive Preference Learning (CPL)☆147Updated 6 months ago
- ☆65Updated 2 months ago
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆175Updated 3 months ago
- Official Repo of LangSuitE☆74Updated last month
- [ICCV'23] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models☆139Updated 3 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆84Updated 5 months ago
- CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.☆85Updated last week
- A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM☆60Updated 3 weeks ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆186Updated 6 months ago
- An extensible benchmark for evaluating large language models on planning☆248Updated 3 months ago
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆239Updated this week
- Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning☆176Updated this week
- A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)☆116Updated last week
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆349Updated 11 months ago
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆202Updated 2 months ago
- ☆57Updated last year
- A collection of LLM with RL papers☆213Updated 4 months ago
- Implementation of TWOSOME☆42Updated 4 months ago