AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Learning Cooperative Visual Dialog Agents With Deep Reinforcement Learning

Abhishek Das, Satwik Kottur, Jose M. F. Moura, Stefan Lee, Dhruv Batra

ICCV 2017 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Theory-of-mind social reasoning · 387 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
RL fine-tuning of both agents on image guessing rewardQ-bot and A-bot (SL-pretrained) · VisDial v0.5 test image guessing, round 10percentile rank: improving percentile rank by over 3%Improved
RL fine-tuning, human judges guess the imageSL-pretrained dialog · Human studymean rank of ground truth: 3.70 -> 2.73Improved
RL fine-tuning, human judges guess the imageSL-pretrained dialog · Human studyMRR: 0.518 -> 0.622Improved
add multi-task SL answer loss to RL image-guessing reward (Frozen-Q-multi)Frozen-Q A-bot · VisDial v0.5 testmean rank: improving the best reported result by 0.7 mean rank (3%)Improved
RL fine-tuning only (no SL term)A-bot · VisDial v0.5 testMRR, recall@k, mean rankNo clear effect
freeze one agent during RL (Frozen-Q or Frozen-A) (ablation)RL agents · Image guessingpercentile rankHurt

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