AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Interferobot: aligning an optical interferometer by a reinforcement learning agent

Dmitry Sorokin, Alexander Ulanov, Ekaterina Sazhina, Alexander Lvovsky

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL · 5 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 radius randomization (ablation)Interferobot DDQN agent · physical MZIvisibility: 0.74 ± 0.20 -> 0.96 ± 0.02Improved
add radius randomization (ablation)Interferobot DDQN agent · physical MZIreturn: 85 ± 69 -> 221 ± 54Improved
add white noise to pixels (ablation)Interferobot DDQN agent · physical MZIvisibility: 0.82 ± 0.07 -> 0.96 ± 0.02Improved
add white noise to pixels (ablation)Interferobot DDQN agent · physical MZIreturn: 129 ± 43 -> 221 ± 54Improved
add brightness randomization (ablation)Interferobot DDQN agent · physical MZIvisibility: 0.91 ± 0.04 -> 0.96 ± 0.02Improved
add brightness randomization (ablation)Interferobot DDQN agent · physical MZIreturn: 178 ± 39 -> 221 ± 54Improved
add duty cycle and trigger time randomization (ablation)Interferobot DDQN agent · physical MZIvisibility: 0.89 ± 0.07 -> 0.96 ± 0.02Improved
add duty cycle and trigger time randomization (ablation)Interferobot DDQN agent · physical MZIreturn: 200 ± 42 -> 221 ± 54Improved
deploy on physical setup instead of simulatorInterferobot DDQN agent · simulation vs physical MZImean highest visibility: 0.986 -> 0.983Hurt
RL agent versus human expert using keyboardInterferobot DDQN agent · physical MZImean highest visibility: 0.972 -> 0.983Improved
RL agent versus human manual knob alignmentInterferobot DDQN agent · physical MZItime to fine-tuned alignment: 0.968Mixed

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