PoE-World: Compositional World Modeling with Products of Programmatic Experts

• URL: http://arxiv.org/abs/2505.10819v2
• Date: Thu, 22 May 2025 09:02:44 GMT
• Title: PoE-World: Compositional World Modeling with Products of Programmatic Experts
• Authors: Wasu Top Piriyakulkij, Yichao Liang, Hao Tang, Adrian Weller, Marta Kryven, Kevin Ellis,
• Abstract summary: Learning how the world works is central to building AI agents that can adapt to complex environments.<n>Recent advances in program synthesis using Large Language Models (LLMs) give an alternate approach which learns world models represented as source code.<n>We show that this approach can learn complex world models from just a few observations. We evaluate the learned world models by embedding them in a model-based planning agent, demonstrating efficient performance and generalization to unseen levels on Atari's Pong and Montezuma's Revenge.
• Score: 41.07916209987106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning how the world works is central to building AI agents that can adapt to complex environments. Traditional world models based on deep learning demand vast amounts of training data, and do not flexibly update their knowledge from sparse observations. Recent advances in program synthesis using Large Language Models (LLMs) give an alternate approach which learns world models represented as source code, supporting strong generalization from little data. To date, application of program-structured world models remains limited to natural language and grid-world domains. We introduce a novel program synthesis method for effectively modeling complex, non-gridworld domains by representing a world model as an exponentially-weighted product of programmatic experts (PoE-World) synthesized by LLMs. We show that this approach can learn complex, stochastic world models from just a few observations. We evaluate the learned world models by embedding them in a model-based planning agent, demonstrating efficient performance and generalization to unseen levels on Atari's Pong and Montezuma's Revenge. We release our code and display the learned world models and videos of the agent's gameplay at https://topwasu.github.io/poe-world.

Related papers

• AdaWorld: Learning Adaptable World Models with Latent Actions [76.50869178593733]
  We propose AdaWorld, an innovative world model learning approach that enables efficient adaptation.<n>Key idea is to incorporate action information during the pretraining of world models.<n>We then develop an autoregressive world model that conditions on these latent actions.
  arXiv  Detail & Related papers  (2025-03-24T17:58:15Z)
• Multimodal Dreaming: A Global Workspace Approach to World Model-Based Reinforcement Learning [2.5749046466046903]
  In Reinforcement Learning (RL), world models aim to capture how the environment evolves in response to the agent's actions.<n>We show that performing the dreaming process inside the latent space allows for training with fewer environment steps.<n>We conclude that the combination of GW with World Models holds great potential for improving decision-making in RL agents.
  arXiv  Detail & Related papers  (2025-02-28T15:24:17Z)
• Text2World: Benchmarking Large Language Models for Symbolic World Model Generation [45.03755994315517]
  We introduce a novel benchmark, Text2World, based on planning domain definition language (PDDL)<n>We find that reasoning models trained with large-scale reinforcement learning outperform others.<n>Building on these insights, we examine several promising strategies to enhance the world modeling capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-02-18T17:59:48Z)
• Pandora: Towards General World Model with Natural Language Actions and Video States [61.30962762314734]
  Pandora is a hybrid autoregressive-diffusion model that simulates world states by generating videos and allows real-time control with free-text actions. Pandora achieves domain generality, video consistency, and controllability through large-scale pretraining and instruction tuning.
  arXiv  Detail & Related papers  (2024-06-12T18:55:51Z)
• Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models [51.891804790725686]
  Elements of World Knowledge (EWoK) is a framework for evaluating language models' understanding of conceptual knowledge underlying world modeling.<n>EWoK-core-1.0 is a dataset of 4,374 items covering 11 world knowledge domains.<n>All tested models perform worse than humans, with results varying drastically across domains.
  arXiv  Detail & Related papers  (2024-05-15T17:19:42Z)
• WorldGPT: Empowering LLM as Multimodal World Model [51.243464216500975]
  We introduce WorldGPT, a generalist world model built upon Multimodal Large Language Model (MLLM) WorldGPT acquires an understanding of world dynamics through analyzing millions of videos across various domains. We conduct evaluations on WorldNet, a multimodal state transition prediction benchmark.
  arXiv  Detail & Related papers  (2024-04-28T14:42:02Z)
• WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment [11.81398773711566]
  We give a model-based agent that builds a Python program representing its knowledge of the world based on its interactions with the environment. We study our agent on gridworlds, and on task planning, finding our approach is more sample-efficient compared to deep RL, more compute-efficient compared to ReAct-style agents, and that it can transfer its knowledge across environments by editing its code.
  arXiv  Detail & Related papers  (2024-02-19T16:39:18Z)
• WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens [75.02160668328425]
  We introduce WorldDreamer, a pioneering world model to foster a comprehensive comprehension of general world physics and motions. WorldDreamer frames world modeling as an unsupervised visual sequence modeling challenge. Our experiments show that WorldDreamer excels in generating videos across different scenarios, including natural scenes and driving environments.
  arXiv  Detail & Related papers  (2024-01-18T14:01:20Z)
• Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents [111.15288256221764]
  Grounded-decoding project aims to solve complex, long-horizon tasks in a robotic setting by leveraging the knowledge of both models. We frame this as a problem similar to probabilistic filtering: decode a sequence that both has high probability under the language model and high probability under a set of grounded model objectives. We demonstrate how such grounded models can be obtained across three simulation and real-world domains, and that the proposed decoding strategy is able to solve complex, long-horizon tasks in a robotic setting by leveraging the knowledge of both models.
  arXiv  Detail & Related papers  (2023-03-01T22:58:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.