AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Interaction-Grounded Learning with Action-Inclusive Feedback

Tengyang Xie, Akanksha Saran, Dylan J Foster, Lekan P Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 2 citations (OpenAlex)

Read the paper

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
Use action-specific contrastive reward decoding and symmetry breaking instead of the full-conditional-independence IGL methodIGL · MNIST (action-inclusive feedback)policy accuracy (%): 9.18 ± 2.10 -> 83.63 ± 1.25Improved
Use action-specific contrastive reward decoding and symmetry breaking instead of the full-conditional-independence IGL methodIGL · Simulated BCI (1% noise)policy accuracy: 32.60±0.24 -> 89.10 ± 3.58Improved
Use action-specific contrastive reward decoding and symmetry breaking instead of the full-conditional-independence IGL methodIGL · Simulated BCI (5% noise)policy accuracy: 33.75±0.29 -> 76.60 ± 4.09Improved
Use action-specific contrastive reward decoding and symmetry breaking instead of the full-conditional-independence IGL methodIGL · Simulated BCI (10% noise)policy accuracy: 33.33 ± 0.29 -> 64.25 ± 4.16Improved
Use action-specific contrastive reward decoding and symmetry breaking instead of the full-conditional-independence IGL methodIGL · OpenML CC-18 (K≥3)policy accuracy (%): 15.65±2.30 -> 35.74±1.45Improved
Use action-specific contrastive reward decoding and symmetry breaking instead of the full-conditional-independence IGL methodIGL · OpenML CC-18 (K≥3, N≥70000)policy accuracy (%): 11.91±1.80 -> 50.11±2.98Improved
Use AI-IGL rather than IGL (full CI)IGL · MNIST (action-exclusive feedback)policy accuracy (%): 86.13 ± 0.52 -> 86.14 ± 0.94No clear effect
Increase simulated BCI feedback noise from 1% to 10%AI-IGL · Simulated BCIpolicy accuracy: 89.10 ± 3.58 -> 64.25 ± 4.16Hurt
Use AI-IGL instead of contextual bandits with exact rewardContextual bandits · OpenML CC-18 (K≥3)policy accuracy (%): 57.98±5.65 -> 35.74±1.45Hurt

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