Pith. sign in

REVIEW 6 cited by

Learning by Cheating

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 1912.12294 v1 pith:UTQ4SKMK submitted 2019-12-27 cs.RO cs.AIcs.CVcs.LG

Learning by Cheating

classification cs.RO cs.AIcs.CVcs.LG
keywords agentbenchmarkprivilegedfirstvision-basedaccessapproachautonomous
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Vision-based urban driving is hard. The autonomous system needs to learn to perceive the world and act in it. We show that this challenging learning problem can be simplified by decomposing it into two stages. We first train an agent that has access to privileged information. This privileged agent cheats by observing the ground-truth layout of the environment and the positions of all traffic participants. In the second stage, the privileged agent acts as a teacher that trains a purely vision-based sensorimotor agent. The resulting sensorimotor agent does not have access to any privileged information and does not cheat. This two-stage training procedure is counter-intuitive at first, but has a number of important advantages that we analyze and empirically demonstrate. We use the presented approach to train a vision-based autonomous driving system that substantially outperforms the state of the art on the CARLA benchmark and the recent NoCrash benchmark. Our approach achieves, for the first time, 100% success rate on all tasks in the original CARLA benchmark, sets a new record on the NoCrash benchmark, and reduces the frequency of infractions by an order of magnitude compared to the prior state of the art. For the video that summarizes this work, see https://youtu.be/u9ZCxxD-UUw

discussion (0)

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

Forward citations

Cited by 6 Pith papers

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

  1. Privileged Foresight Distillation: Zero-Cost Future Correction for World Action Models

    cs.RO 2026-04 unverdicted novelty 7.0

    Privileged Foresight Distillation distills the residual difference in action predictions with versus without future context into a current-only adapter, yielding consistent gains on LIBERO and RoboTwin benchmarks.

  2. Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

    cs.CV 2026-05 conditional novelty 6.0

    VLA-AD distills 7B VLA teachers into 158M students using offline VLM semantic guidance on task phases and directions, matching teacher performance on LIBERO with 44x size reduction and 3.28x speedup.

  3. Self-Distilled Agentic Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 5.0

    SDAR gates on-policy self-distillation signals into RL training to stabilize and improve multi-turn LLM agent performance on ALFWorld, WebShop, and Search-QA.

  4. InterFuserDVS: Event-Enhanced Sensor Fusion for Safe RL-Based Decision Making

    cs.CV 2026-05 unverdicted novelty 5.0

    Integrating DVS event data into InterFuser through token fusion yields a driving score of 77.2 and 100% route completion on CARLA benchmarks, indicating improved robustness in dynamic conditions.

  5. Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA

    cs.RO 2026-04 unverdicted novelty 5.0

    Semantic rollout prediction plus town-adversarial regularization on a Dreamer agent raises mean zero-shot success rate for fixed-route driving across held-out CARLA towns under fixed weather and no traffic.

  6. Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA

    cs.RO 2026-04 unverdicted novelty 5.0

    Semantic rollout plus town-adversarial regularization raises zero-shot success in held-out CARLA towns to 36.6% and 85.6% versus matched DreamerV3 baselines.