AI Paper Atlas

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

Entropic Desired Dynamics for Intrinsic Control

Steven Stenberg Hansen, Guillaume Desjardins, Kate Baumli, David Warde-Farley, Nicolas Heess, Simon Osindero, Volodymyr Mnih

NeurIPS 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Intrinsically motivated exploration · 0 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 additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Montezuma's Revengeaverage return: 0 -> 30.9Improved
add additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Montezuma's Revengelifetime coverage (x10^3): 4.54 -> 8.07Improved
add additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Berzerklifetime coverage (x10^3): 10.6 -> 61.3Improved
add additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Berzerkepisodic coverage and average return: 0.562 -> 0.382 episodic; 584 -> 477 returnHurt
add additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Heroaverage return: 68.7 -> 1.34kImproved
add additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Private Eyeaverage return: -43.6 -> 1.07kImproved
add additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Ms. Pacmanaverage return: 360 -> 587Improved
add additive latent dynamics z_i+Delta_i (EDDICT) in place of independent per-option codes (EDDICT-∆) (ablation)EDDICT · Seaquestaverage return: 238 -> 400Improved
use globally consistent Markov-chain codes (EDDICT) instead of relative-only codes of RVICEDDICT · Montezuma's Revengeaverage return: 0 -> 30.9Improved
use EDDICT instead of RVICEDDICT · Berzerklifetime coverage (x10^3): 31.3 -> 61.3Improved
use EDDICT instead of RVICEDDICT · Heroepisodic coverage and average return: 2.58 -> 2.1 episodic; 805 -> 1.34k returnMixed
use EDDICT instead of RVICEDDICT · Private Eyeepisodic coverage and average return: 5.41 -> 4.86 episodic; 886 -> 1.07k returnMixed

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