AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

APPLE: Toward General Active Perception via Reinforcement Learning

Tim Schneider, Cristiana de Farias, Roberto Calandra, Liming Chen, Jan Peters

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior

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
learn exploration with APPLE (SAC or CrossQ) instead of a random policy (ablation)APPLE · CircleSquarefinal accuracy (%): 68% -> 97% (SAC)Improved
learn exploration with APPLE instead of a random policy (ablation)APPLE · TactileMNISTfinal accuracy (%): 74% -> 89% (CrossQ)Improved
learn exploration with APPLE instead of a random policy (ablation)APPLE · TactileMNISTVolumefinal error (cm^3): 1.07 -> 0.99 (SAC); 1.05 (CrossQ)No clear effect
use APPLE-CrossQ rather than SAC without tuning on the task (ablation)APPLE · Toolboxpose errorImproved
use CrossQ (no target networks) instead of SAC (ablation)APPLE · training costtraining time: 53% reduction in training time on averageImproved
use on-policy PPO instead of off-policy SAC/CrossQ (ablation)APPLE · CircleSquarefinal accuracy (%): 79% (PPO) vs 96-97% (CrossQ, SAC)Hurt
replace transformer with LSTM (HAM-style model) (ablation)APPLE · CircleSquareconvergence speed: PPO: 79% -> 72%Hurt
remove supervised prediction loss and label (pure RL) (ablation)APPLE · CircleSquarefinal accuracy (%): peaks at 80%Hurt
replace learned exploration with static grid search (ablation)APPLE · CircleSquarefinal accuracy (%): stagnates at 73%Hurt
share embeddings across Q-networks, action policy and prediction policy (ablation)APPLE · tactile tasksperformanceImproved
use HAM (REINFORCE, LSTM) instead of APPLEHAM · CircleSquarefinal accuracyHurt

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