AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

GPLAC: Generalizing Vision-Based Robotic Skills Using Weakly Labeled Images

Avi Singh, Larry Yang, Sergey Levine

ICCV 2017 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add attention architecture to classifier-augmented CNN (ablation)GPLAC · Pusher (simulation, unseen envs)success rate (%): 2.25 -> 79.75Improved
add attention architecture to classifier-augmented CNN (ablation)GPLAC · Striker (simulation, unseen envs)success rate (%): 21.50 -> 59.25Improved
add weakly labeled data via binary classifier (ablation)ATT-1 · Pusher (simulation, unseen envs)success rate (%): 37.50 -> 79.75Improved
add weakly labeled data via binary classifier (ablation)ATT-1 · Striker (simulation, unseen envs)success rate (%): 35.50 -> 59.25Improved
add weakly labeled data via binary classifier (ablation)ATT-1 · Real robot mug pushingsuccess rate (%): 33.22 -> 56.36Improved
add domain adaptation on top of GPLACGPLAC · Pusher (simulation, unseen envs)success rate (%): 79.75 -> 66.50Hurt
add domain adaptation on top of GPLACGPLAC · Striker (simulation, unseen envs)success rate (%): 59.25 -> 61.00Improved
use binary classifier instead of domain adaptation for weak data (ablation)ATT-DA · Pusher (simulation, unseen envs)success rate (%): 69.50 -> 79.75Improved
use binary classifier instead of domain adaptation for weak data (ablation)ATT-DA · Striker (simulation, unseen envs)success rate (%): 40.50 -> 59.25Improved
reduce weakly labeled images from 80000 to 800 (ablation)GPLAC · Pusher (simulation, unseen envs)success rate (%): 79.75 -> 78.50No clear effect
reduce weakly labeled images from 800 to 80 (ablation)GPLAC · Pusher (simulation, unseen envs)success rate (%): 78.50 -> 56.00Hurt
reduce weakly labeled images from 800 to 80 (ablation)GPLAC · Striker (simulation, unseen envs)success rate (%): 53.00 -> 33.50Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy