AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents

Marco Pleines, Matthias Pallasch, Frank Zimmer, Mike Preuss

JMLR 2025 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 4 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 observation reconstruction loss (ablation)TrXL · Finite tasks aggregatemean task progression: 56% -> 99%Improved
add observation reconstruction loss (ablation)GRU · Searing Spotlightssample efficiencyImproved
replace TrXL with GRUPPO agent · Endless Mortar Mayhemcommands executed: 17 -> 115Improved
replace TrXL with GRUPPO agent · Endless Searing Spotlightscoins collected: 6.7 -> 23.9Improved
replace TrXL with GRUPPO agent · Endless Mystery Pathtiles visited: 20 -> 26Improved
scale TrXL layers, embedding and memory window (ablation)TrXL · Endless Mortar Mayhemcommands executedNo clear effect
add ground truth estimation head (ablation)TrXL · Endless Mortar Mayhemmean commands: 16 -> 36Improved
raise final learning rate to 1e-4 (ablation)TrXL · Endless Mortar Mayhemmean commands: 16 -> 25Improved
add absolute positional encoding to query (ablation)TrXL · Endless Mortar Mayhemmean commands: 16 -> 18Improved
combine tuned LR, query positional encoding and ground truth head (ablation)TrXL · Endless Mortar Mayhemmean commands: 16 -> 47Improved
use learned or relative positional encoding (ablation)TrXL · Endless Mortar Mayhemmean commandsNo clear effect
turn off advantage normalization (ablation)recurrent PPO agent · Searing Spotlights (full observability)success rate: 0.43 -> 1.00Improved

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