Pith. sign in

REVIEW 2 cited by

Reward (Mis)design for Autonomous Driving

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 2104.13906 v2 pith:YDXSNRLA submitted 2021-04-28 cs.LG

classification cs.LG
keywords rewarddesignfunctionsautonomouscheckscommondrivingerrors
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This article considers the problem of diagnosing certain common errors in reward design. Its insights are also applicable to the design of cost functions and performance metrics more generally. To diagnose common errors, we develop 8 simple sanity checks for identifying flaws in reward functions. These sanity checks are applied to reward functions from past work on reinforcement learning (RL) for autonomous driving (AD), revealing near-universal flaws in reward design for AD that might also exist pervasively across reward design for other tasks. Lastly, we explore promising directions that may aid the design of reward functions for AD in subsequent research, following a process of inquiry that can be adapted to other domains.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving

    cs.LG 2025-05 reject novelty 6.0 of 10

    A responsibility-aware crash penalty, built from a traffic-law knowledge graph and a vision-language blame classifier, improves MetaDrive success rates and shifts reported collision blame away from the ego vehicle.

  2. Residual Reward Models for Preference-based Reinforcement Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Combining a hand-designed or learned prior reward with a preference-trained residual improves sample efficiency and final performance in preference-based reinforcement learning.

Pith tools