paper-with-me

홈 › Papers

World Programs for Model-Based Learning and Planning in Compositional State and Action Spaces

2019-12-30 · Marwin H. S. Segler

Some of the most important tasks take place in environments which lack cheap and perfect simulators, thus hampering the application of model-free reinforcement learning (RL). While model-based RL aims to learn a dynamics model, in a more general case the learner does not know a priori what the action space is. Here we propose a formalism where the learner induces a world program by learning a dynamics model and the actions in graph-based compositional environments by observing state-state transition examples. Then, the learner can perform RL with the world program as the simulator for complex planning tasks. We highlight a recent application, and propose a challenge for the community to assess world program-based planning.

📄 PDF Abstract BibTeX arXiv:1912.13007

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Learning Compositional Neural Programs for Continuous Control

2020-07-27 · Thomas Pierrot, Nicolas Perrin, Feryal Behbahani, Alexandre Laterre 외

We propose a novel solution to challenging sparse-reward, continuous control problems that require hierarchical planning at multiple levels of abstraction. Our solution, dubbed AlphaNPI-X, involves three separate stages …

continuous-controlContinuous Control

Compositional Planning with Jumpy World Models

2026-02-23 · Jesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Marc G. Bellemare 외 arxiv

The ability to plan with temporal abstractions is central to intelligent decision-making. Rather than reasoning over primitive actions, we study agents that compose pre-trained policies as temporally extended actions, en…

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

2024-04-16 · Hongxin Zhang, Zeyuan Wang, Qiushi Lyu, Zheyuan Zhang 외

In this paper, we investigate the problem of embodied multi-agent cooperation, where decentralized agents must cooperate given only egocentric views of the world. To effectively plan in this setting, in contrast to learn…

Learning compositional programs with arguments and sampling

2021-09-01 · NeurIPS Workshop AIPLANS 2021 12 · Giovanni De Toni, Luca Erculiani, Andrea Passerini

One of the most challenging goals in designing intelligent systems is empowering them with the ability to synthesize programs from data. Namely, given specific requirements in the form of input/output pairs, the goal is …

Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes

2023-01-04 · Justin Reppert, Ben Rachbach, Charlie George, Luke Stebbing 외

Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but m…