AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Reinforcement Learning with Fast and Forgetful Memory

Steven Morad, Ryan Kortvelesy, Stephan Liwicki, Amanda Prorok

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous 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
Replace recurrent memory with FFMrecurrent RL models · POPGymMMER: 0.349 -> 0.400Improved
Add input gating (ablation)FFM · POPGym tasksmean reward (μ): 0.392 -> 0.399Improved
Add output gating (ablation)FFM · POPGym tasksmean reward (μ): 0.395 -> 0.399Improved
Add temporal context (ablation)FFM · POPGym tasksmean reward (μ): 0.382 -> 0.399Improved
Learn context rather than fixing it (ablation)FFM · POPGym tasksmean reward (μ): 0.383 -> 0.399Improved
Add decay (forgetting) (ablation)FFM · POPGym tasksmean reward (μ): 0.333 -> 0.399Improved
Learn decay rather than fixing it (ablation)FFM · POPGym tasksmean reward (μ): 0.390 -> 0.399Improved
Use the outer product rather than the Hadamard product for γ (ablation)FFM · POPGym tasksmean reward (μ): 0.395 -> 0.399Improved

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