AI Paper Atlas

Research map / Reinforcement learning / Offline RL

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

Daesol Cho, Dongseok Shim, H. Jin Kim

NeurIPS 2022 · Reinforcement learning › Offline RL · approach: Offline RL sample complexity theory · 3 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 S2P augmented images (50k extra)IQL · DMControl cheetah run (mixed)normalized score: 41.68 -> 88.53Improved
add S2P augmented imagesSLAC-off · DMControl walker walk (mixed)normalized score: 29.02 -> 92.60Improved
add S2P augmented imagesCQL · DMControl reacher easy (expert)normalized score: 57.68 -> 32.54Hurt
add S2P augmented imagesIQL · DMControl finger spin (expert)normalized score: 98.42 -> 94.42Hurt
rollout with offline-RL policy instead of random policy (ablation)CQL+S2P · cheetah run (random)normalized score: -0.69 -> 11.77Improved
rollout with random policy instead of offline-RL policy (ablation)IQL+S2P · cheetah run (expert)normalized score: 79.20 -> 87.18Improved
replace Max Var with Ens Var uncertainty (ablation)CQL+S2P · cheetah run (random)normalized score: 11.77 -> 19.83Improved
replace Max Var with Ens Var uncertainty (ablation)IQL+S2P · cheetah run (expert)normalized score: 87.18 -> 62.41Hurt
increase rollout horizon from 1 to 5 steps (ablation)IQL+S2P · cheetah run (mixed)normalized score: 88.53 -> 66.38Hurt
increase rollout horizon from 1 to 5 steps (ablation)SLAC-off+S2P · cheetah run (expert)normalized score: 14.41 -> 17.17Improved
add S2P data to policy-constraint methodsBC · cheetah mixednormalized score: 51.81 -> 0.06Hurt
replace S2P images with Dreamer images (ablation)IQL · cheetah run (mixed)normalized score: 88.53 -> 2.09Hurt

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