AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Active Vision Reinforcement Learning under Limited Visual Observability

Jinghuan Shang, Michael S Ryoo

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 2 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 sensorimotor reward that penalizes views with poor motor-action predictability (ablation)SUGARL-DQN · Atari 50x50, no peripheral observationnormalized IQM: 0.421 -> 0.805Improved
Add reward balancing (ablation)SUGARL-DQN · Atari 50x50, no peripheral observationnormalized IQM: 0.423 -> 0.805Improved
Add Persistence-of-Vision Memory (ablation)SUGARL-DQN · Atari 50x50, no peripheral observationnormalized IQM: 0.360 -> 0.423Improved
Replace positive intrinsic reward with negative prediction-error reward (ablation)SUGARL-DQN · Atari 50x50, no peripheral observationnormalized IQM: 0.322 -> 0.360Improved
Add joint learning of motor and sensory policies (ablation)SUGARL-DQN · Atari 50x50, no peripheral observationnormalized IQM: 0.171 -> 0.805Improved
Use separate sensory and motor policies rather than one combined action policyDrQ · DMC 20x20normalized IQM: 0.540 -> 0.686Improved
Use separate sensory and motor policies rather than one combined action policyDrQ · DMC 30x30normalized IQM: 0.570 -> 0.717Improved
Use separate sensory and motor policies rather than one combined action policyDrQ · DMC 50x50normalized IQM: 0.776 -> 1.052Improved
Use absolute rather than relative sensory controlSUGARL-DQN · Atari 20x20, no peripheral observationnormalized IQM: 0.367 -> 0.475Improved
Use relative rather than absolute sensory controlSUGARL-DQN · Atari 50x50, no peripheral observationnormalized IQM: 0.805 -> 0.945Improved
Train for 5M rather than 1M stepsSUGARL-DQN · Atari 50x50, no peripheral observationnormalized IQM: 0.805 -> 1.553Improved
Replace SAC entropy autotuning with fixed sensory-policy alphaSUGARL-SAC · Atari 20x20, no peripheral observationnormalized IQM: 0.271 -> 0.424Improved

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