AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation

Lin Guan, Mudit Verma, Sihang Guo, Ruohan Zhang, Subbarao Kambhampati

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 13 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 human visual explanation and context-aware data augmentation to evaluative feedbackEfficient DQN with human feedback · Pixel-Taxi and Pongenvironment and feedback samples to learn a near-optimal policy: 35% less environment samples/ feedback samplesImproved
Add human visual explanation and context-aware data augmentation to evaluative feedbackEfficient DQN with human feedback · Enduro-1000score at a given environment sample count: over 60 by using 80k samples compared to 120k samples used by DQN-TAMER, an over 30% improvementImproved
Add human visual explanation to evaluative feedbackEfficient DQN with human feedback · MR Level 1policy performanceNo clear effect
Add human visual explanation to evaluative feedbackEfficient DQN with human feedback · Asterix and MR Level 1scoreImproved
Replace context-aware augmentation with Gaussian blurring or random croppingEXPAND · Atari games and Pixel-Taxipolicy performanceHurt
Use Ex-AGIL's separate attention prediction network and mask the policy inputDQN-Feedback · Pongpolicy performanceImproved
Use Ex-AGIL's separate attention prediction network and mask the policy inputDQN-Feedback · visually complex environmentspolicy performanceHurt
Add Attention-Align's attention alignment lossEfficient DQN with feedback · all five tasksusable policy learningHurt
Remove the invariance loss (ablation)EXPAND · synthetic-oracle taskspolicy performanceHurt
Remove augmented data from the advantage loss (ablation)EXPAND · synthetic-oracle taskspolicy performanceHurt
Increase augmentations per evaluated state from 5 to 12 (ablation)EXPAND · Pixel-Taxi and Pongpolicy performanceImproved
Use fixed Gaussian filters instead of randomly sampled filters (ablation)Context-agnostic Gaussian-blurring augmentation · Atari games and Pixel-Taxipolicy performanceNo clear effect

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