Pith. sign in

REVIEW 5 cited by

A Generalist Dynamics Model for Control

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.10912 v2 pith:2BBY2EFX submitted 2023-05-18 cs.AI cs.RO

A Generalist Dynamics Model for Control

Ingmar Schubert , Jingwei Zhang , Jake Bruce , Sarah Bechtle , Emilio Parisotto , Martin Riedmiller , Jost Tobias Springenberg , Arunkumar Byravan
show 2 more authors
Leonard Hasenclever Nicolas Heess
This is my paper
classification cs.AI cs.RO
keywords tdmscontroldynamicsgeneralistmodelssettingenvironmentgeneralizing
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen environments, both in a few-shot setting, where a generalist TDM is fine-tuned with small amounts of data from the target environment, and in a zero-shot setting, where a generalist TDM is applied to an unseen environment without any further training. Here, we demonstrate that generalizing system dynamics can work much better than generalizing optimal behavior directly as a policy. Additional results show that TDMs also perform well in a single-environment learning setting when compared to a number of baseline models. These properties make TDMs a promising ingredient for a foundation model of control.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Advantage-Guided Diffusion for Model-Based Reinforcement Learning

    cs.AI 2026-04 unverdicted novelty 7.0

    Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.

  2. TD-MPC2: Scalable, Robust World Models for Continuous Control

    cs.LG 2023-10 conditional novelty 6.0

    TD-MPC2 scales an implicit world-model RL method to a 317M-parameter agent that masters 80 tasks across four domains with a single hyperparameter configuration.

  3. Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension

    cs.MA 2026-05 unverdicted novelty 5.0

    Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.

  4. WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems

    cs.LG 2026-03 unverdicted novelty 5.0

    WestWorld introduces a scalable trajectory world model with Sys-MoE routing via system embeddings and structural embeddings for physical knowledge, pretrained on 89 environments to improve zero-shot prediction and rea...

  5. Simulus: Combining Improvements in Sample-Efficient World Model Agents

    cs.LG 2025-02 unverdicted novelty 5.0

    Simulus integrates flexible tokenization, intrinsic motivation, prioritized world model replay, and regression-as-classification to achieve state-of-the-art sample efficiency for planning-free world model agents on vi...