PDDLGym: Gym Environments from PDDL Problems

2020-02-15 · Tom Silver, Rohan Chitnis

We present PDDLGym, a framework that automatically constructs OpenAI Gym environments from PDDL domains and problems. Observations and actions in PDDLGym are relational, making the framework particularly well-suited for research in relational reinforcement learning and relational sequential decision-making. PDDLGym is also useful as a generic framework for rapidly building numerous, diverse benchmarks from a concise and familiar specification language. We discuss design decisions and implementation details, and also illustrate empirical variations between the 20 built-in environments in terms of planning and model-learning difficulty. We hope that PDDLGym will facilitate bridge-building between the reinforcement learning community (from which Gym emerged) and the AI planning community (which produced PDDL). We look forward to gathering feedback from all those interested and expanding the set of available environments and features accordingly. Code: https://github.com/tomsilver/pddlgym

📄 PDF Abstract BibTeX arXiv:2002.06432

Code (2)

tomsilver/pddlgym 공식 구현

azfeng8/pddlgym

Tasks

Decision Making OpenAI Gym reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Sequential Decision Making

PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning

2026-08-17 · Veit Laule, Jiangtao Shuai, Manfred Hauswirth, Sonja Schimmler arxiv

LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans. Recent hybrid methods instead translate natural language into the Planning Domain Definition Language (PD…

RAMP: Hybrid DRL for Online Learning of Numeric Action Models

2026-04-09 · Yarin Benyamin, Argaman Mordoch, Shahaf S. Shperberg, Roni Stern arxiv

Automated planning algorithms require an action model specifying the preconditions and effects of each action, but obtaining such a model is often hard. Learning action models from observations is feasible, but existing …

Reinforcement Learning

Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models

2024-07-17 · Sadegh Mahdavi, Raquel Aoki, Keyi Tang, Yanshuai Cao

Large Language Models (LLMs) have shown remarkable performance in various natural language tasks, but they often struggle with planning problems that require structured reasoning. To address this limitation, the conversi…

Policy-Guided Lazy Search with Feedback for Task and Motion Planning

2022-10-25 · Mohamed Khodeir, Atharv Sonwane, Ruthrash Hari, Florian Shkurti

PDDLStream solvers have recently emerged as viable solutions for Task and Motion Planning (TAMP) problems, extending PDDL to problems with continuous action spaces. Prior work has shown how PDDLStream problems can be red…

Motion Planning Task and Motion Planning

NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning

2025-10-22 · Wonje Choi, Jooyoung Kim, Honguk Woo arxiv

We address the challenge of adopting language models (LMs) for embodied tasks in dynamic environments, where online access to large-scale inference engines or symbolic planners is constrained due to latency, connectivity…