mlsanityData to 7 Oct 2026

PDDLGym: Gym Environments from PDDL Problems

arXiv 2002.06432 ↗First posted 15 Feb 2020cs.AIcited by 45

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 8; 2023: 3; 2024: 6; 2025: 15; 2026: 10.

45 papers.

Sort:

By area:

  1. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
  2. 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
  3. 2024DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Modelscited by 33
  4. 2023Vision-Language Interpreter for Robot Task Planningcited by 29
  5. 2021Classical Planning in Deep Latent Spacecited by 21
  6. 2021Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generatorscited by 21
  7. 2024Planning in the Dark: LLM-Symbolic Planning Pipeline without Expertscited by 15
  8. 2025NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domainscited by 15
  9. 2022Explainable Reinforcement Learning via Model Transformscited by 11
  10. 2022Goal Recognition as Reinforcement Learningcited by 9
  11. 2022PG3: Policy-Guided Planning for Generalized Policy Generationcited by 8
  12. 2022pyRDDLGym: From RDDL to Gym Environmentscited by 8
33 more
  1. 2023MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worldscited by 5
  2. 2025NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoningcited by 5
  3. 2024NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worldscited by 4
  4. 2025Simulation to Rules: A Dual-VLM Framework for Formal Visual Planningcited by 4
  5. 2025Open-Ended Goal Inference through Actions and Language for Human-Robot Collaborationcited by 3
  6. 2022Learning First-Order Symbolic Planning Representations That Are Groundedcited by 2
  7. 2025An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMscited by 2
  8. 2025Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planningcited by 2
  9. 2026Under the Influence: Quantifying Persuasion and Vigilance in Large Language Modelscited by 2
  10. 2026Learning Lifted Action Models from Unsupervised Visual Tracescited by 2
  11. 2021Learning Causal Models of Autonomous Agents using Interventionscited by 1
  12. 2025Learning Hierarchical Domain Models Through Environment-Grounded Interactioncited by 1
  13. 2025HDDLGym: A Tool for Studying Multi-Agent Hierarchical Problems Defined in HDDL with OpenAI Gymcited by 1
  14. 2025Diverse Planning with Simulators via Linear Temporal Logiccited by 1
  15. 2026ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systemscited by 1
  16. 2026Robots Influencing Humans to Reveal their Goals during Collaboration and Competitioncited by 1
  17. 2022Neural NID Rulescited by 0
  18. 2022The Sandbox Environment for Generalizable Agent Research (SEGAR)cited by 0
  19. 2023Human in the Loop Novelty Generationcited by 0
  20. 2024Meta-operators for Enabling Parallel Planning Using Deep Reinforcement Learningcited by 0
  21. 2024A Research Agenda for Usability and Generalisation in Reinforcement Learningcited by 0
  22. 2025Guided Exploration for Efficient Relational Model Learningcited by 0
  23. 2025OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflectionscited by 0
  24. 2025Integrating Symbolic RL Planning into a BDI-based Autonomous UAV Framework: System Integration and SIL Validationcited by 0
  25. 2025Revisiting Landmarks: Learning from Previous Plans to Generalize over Problem Instancescited by 0
  26. 2025Neuro-Logic Lifelong Learningcited by 0
  27. 2025Autonomous Assessment of Generalizability of AI Agent Capabilitiescited by 0
  28. 2026RAMP: Hybrid DRL for Online Learning of Numeric Action Modelscited by 0
  29. 2026SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learningcited by 0
  30. 2026Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Gamescited by 0
  31. 2026DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combatcited by 0
  32. 2026PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planningcited by 0
  33. 2026Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanismscited by 0