DaemonIB / GPT-HTN-Planner
A Hierarchical Task Network planner utilizing LLMs like OpenAI's GPT-4 to create complex plans from natural language that can be converted into an executable form.
☆50Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for GPT-HTN-Planner
- The Fast Downward domain-independent classical planning system☆270Updated this week
- A task-planning system based on Pyhop, but generalized to plan for both goals and tasks.☆60Updated 3 years ago
- ☆373Updated last year
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆220Updated last month
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆110Updated 5 months ago
- ☆54Updated 10 months ago
- Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL☆43Updated last month
- Unquestionable PDDL 3.1 parser☆90Updated last month
- A benchmark for evaluating learning agents based on just language feedback☆58Updated last month
- A collection of PDDL generators, some of which have been used to generate benchmarks for the International Planning Competition (IPC).☆86Updated last week
- The official implementation of the paper "Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction".☆32Updated 9 months ago
- An extensible benchmark for evaluating large language models on planning☆293Updated 6 months ago
- A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code you…☆57Updated last month
- LILO: Library Induction with Language Observations☆78Updated 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…☆77Updated 3 months ago
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆62Updated last year
- A re-implementation of Meta-Prompt in LangChain for building self-improving agents.☆60Updated last year
- 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
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆195Updated 2 weeks ago
- ☆78Updated 11 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
- ☆137Updated 6 months ago
- The AIPlan4EU Unified Planning Library☆194Updated this week
- A library for building software agents using behavior trees and language models.☆74Updated 6 months ago
- The newly improved planner (and more) in the cloud.☆31Updated 3 months ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆86Updated last year
- Write planning task as Python classes, then translate to PDDL. Type checking included.☆42Updated last year
- ☆122Updated 3 weeks ago
- ☆22Updated last year
- Repo to reproduce the First-Explore paper results☆36Updated 3 weeks ago