AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Palm up: Playing in the Latent Manifold for Unsupervised Pretraining

Hao Liu, Tom Zahavy, Volodymyr Mnih, Satinder Singh

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 1 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 PALM exploratory pretraining instead of CSICIFAR-10 classifiers · CIFAR-10 → SVHN, CIFAR-100, and Interp.; CIFAR-10 → LSUN and CelebAAUROC (%): 96.5\stdv{0.2} -> 97.9\stdv{0.2}; 90.5\stdv{0.1} -> \bf 91.5\stdv{0.2}; 78.5\stdv{0.2} -> \bf 79.9\stdv{0.2}; \bf 96.3\sMixed
Use PALM pretraining instead of DrQ's no-pretraining setupAtari 100k agents · Atari 100kMedian HNS: 0.268 -> \bf 0.298Improved
Use PALM exploratory pretraining instead of DrQ's no-pretraining setupAtari 100k agents · Atari 100kMean HNS: 0.357 -> \bf 0.411Improved
Use PALM instead of offline-data SGI pretrainingAtari 100k agents · Atari 100kMedian HNS: \textbf{0.753} -> \bf 0.298Hurt
Use PALM instead of offline-data SGI pretrainingAtari 100k agents · Atari 100kMean HNS: \textbf{1.598} -> \bf 0.411Hurt
Add the agent's action to the latent transition rather than ignore it (ablation)PALM · CIFAR-100 classificationAccuracyImproved
Use agent-selected actions rather than random actions (ablation)PALM · CIFAR-100 classificationAccuracyImproved
Add temporal state persistence to the latent transition (ablation)PALM · CIFAR-100 classificationAccuracyImproved
Mix some random latent into the action rather than use action alone (α=1.0) (ablation)PALM · CIFAR-100 classificationAccuracyImproved
Use temporally persistent dynamics rather than reduced persistence (α=0.5, β=0.5) (ablation)PALM · CIFAR-100 classificationAccuracyImproved
Use PALM's explored ordered experience rather than randomly sampled consecutive offline observations (ablation)Passive PALM · CIFAR classificationAccuracyImproved
Interactively explore during training rather than train passively on the same ordered experience (ablation)PALM · CIFAR classificationAccuracyNo clear effect

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