AI Paper Atlas

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

Interesting Object, Curious Agent: Learning Task-Agnostic Exploration

Simone Parisi, Victoria Dean, Deepak Pathak, Abhinav Gupta

NeurIPS 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Intrinsically motivated exploration · 4 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
pre-train one exploration policy across multiple environments and transfer itC-BET · MiniGrid transfertask success rateImproved
add environment-change rarity to state novelty (ablation)C-BET · MiniGrid transfertask success rate: 33.64% vs 28.35%Improved
remove the change-count term (ablation)C-BET · MiniGrid transferaverage success rate: 33.64% vs 28.35%Hurt
remove the state-count term (ablation)C-BET · MiniGrid transferaverage success rate: 33.64% vs 18.15%Hurt
use both the sum and product of state and change terms (ablation)C-BET reward · MiniGrid transferaverage success rate: 33.64% vs 31.9%Hurt
use an alternative state/change reward combination (ablation)C-BET reward · MiniGrid transferaverage success rate: 33.64% vs 30.4%Hurt
count states with panoramic rather than egocentric views (ablation)state-only count · MiniGrid transfer, three pre-training setupsaverage success rate: 28.3% vs 24.9%Mixed
square the state-only reward (ablation)state-only count · MiniGrid transfersuccess rateHurt
encode environment changes with egocentric instead of panoramic views (ablation)C-BET · MiniGrid transfersuccess rateHurt
remove random count resets (ablation)C-BET · MiniGrid transfertask success rateHurt
use change-only counts instead of combined state and change counts (ablation)C-BET · MiniGrid transfersuccess rate: 33.64% vs 18.15%Hurt
pre-train across multiple environments rather than a single environment (ablation)C-BET · MiniGrid transfergeneralization to unseen environmentsImproved

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