AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods

Desi R. Ivanova, Adam Foster, Steven Kleinegesse, Michael U. Gutmann, Tom Rainforth

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 7 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
Use iDAD (InfoNCE) instead of SG-BOEDadaptive design for the SIR Model · SIR ModelMI lower bound: 3.752 -> 3.915Improved
Use iDAD (InfoNCE) instead of the variational myopic approachadaptive design for Location Finding · Location Finding (4D)total EIG lower bound: 4.639 ± 0.144 -> 7.750 ± 0.039Improved
Use iDAD (InfoNCE) instead of likelihood-based DADadaptive design for Location Finding · Location Finding (6D)total EIG lower bound: 6.300 ± 0.030 -> 5.986 ± 0.037Hurt
Use iDAD (InfoNCE) instead of likelihood-based DADadaptive design for Location Finding · Location Finding (4D, 6D, 10D, 20D)total EIG lower bound: 7.967 ± 0.034 -> 7.750 ± 0.039; 6.300 ± 0.030 -> 5.986 ± 0.037; 3.337 ± 0.039 -> 3.251 ± 0.039; 0.937 ± 0.022 -> 0.871 ±Mixed
Use iDAD (InfoNCE) instead of iDAD (NWJ)adaptive design for Location Finding · Location Finding (4D, 6D, 10D, 20D)total EIG lower bound: 7.694 ± 0.045 -> 7.750 ± 0.039; 5.765 ± 0.036 -> 5.986 ± 0.037; 3.252 ± 0.039 -> 3.251 ± 0.039; 0.877 ± 0.022 -> 0.871 ±Mixed
Use iDAD (InfoNCE) rather than iDAD (NWJ)adaptive design for the pharmacokinetic model · Pharmacokinetic modeltotal EIGNo clear effect
Use an attention-based design history encoder instead of pooling (ablation)iDAD design network · Location Findingtotal EIG lower bound: 7.398 ± 0.040 -> 7.750 ± 0.039Improved
Use an attention-based critic history encoder instead of pooling (ablation)iDAD critic network · Location Findingtotal EIG lower bound: 7.567 ± 0.037 -> 7.750 ± 0.039Improved
Use attention in both design and critic history encoders instead of pooling in both (ablation)iDAD · Location Findingtotal EIG lower bound: 7.135 ± 0.034 -> 7.750 ± 0.039Improved

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