AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Scalable Option Learning in High-Throughput Environments

Mikael Henaff, Scott Fujimoto, Michael Matthews, Michael Rabbat

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 0 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 batched single-network hierarchical system (SOL) instead of prior hierarchical implementationshierarchical RL · NLE throughputsteps/second: 55 -> 43000Improved
hierarchical SOL vs flat APPO throughputSOL · NLE throughputsteps/second: 50000 -> 43000No clear effect
add hierarchy with option rewards (SOL) instead of flat APPO with option rewardsAPPO (task+option rewards) · MiniHack TreasureDashpoints: 23 -> 28Improved
add option rewards (Health) to flat APPO task rewardAPPO · NetHackScoregame scoreNo clear effect
use SOL hierarchy with task reward only (HiPPO) instead of option rewards (ablation)SOL+HiPPO · NetHackScoregame scoreNo clear effect
add option rewards and hierarchy together (SOL) over flat agentsSOL · NetHackScoregame scoreImproved
add Motif LLM rewards to SOL Score optionSOL+Motif · NetHackScoregame scoreImproved
learn option rewards with DIAYN instead of hand-specified (ablation)SOL · MiniHackreturnNo clear effect
use SOL instead of flat APPO on hard G-mazeSOL · PointMaze G-mazesuccess rate: 0% -> roughly 70%Improved
use SOL on easy U-MazeSOL · PointMaze U-Mazesuccess rateNo 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