Pith. sign in

REVIEW 1 cited by

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

Not yet reviewed by Pith; the record is open.

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 2103.04909 v3 pith:U3PWPRMC submitted 2021-03-08 cs.LG cs.AIcs.NEcs.RO

classification cs.LGcs.AIcs.NEcs.RO
keywords agentsimaginationlearningmodelstasksworldalgorithmsautonomous
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how such agents generalize to real-world autonomous vehicle control tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the choice of their observation model. We provide extensive empirical evidence for the effectiveness of world models provided with long enough memory horizons in sim2real tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics

    cs.RO 2025-02 conditional novelty 6.0 of 10

    Wheeled Lab is an open-source ecosystem that trains three zero-shot RL policies on low-cost wheeled robots in Isaac Lab and deploys them in the real world.

Pith tools