AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Structured State Space Models for In-Context Reinforcement Learning

Chris Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Nicolaus Foerster, Satinder Singh, Feryal Behbahani

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 11 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 GRU with S5 (reset-capable) recurrent layerrecurrent PPO agent · POPGym Repeat Previous HardMMER: -0.46 -> 0.91Improved
replace GRU with S5recurrent PPO agent · POPGym Noisy Stateless Pendulum HardMMER: 0.61 -> 0.55Hurt
replace GRU with S5recurrent PPO agent · POPGym Stateless Pendulum HardMMER: 0.75 -> 0.79Improved
replace GRU with S5recurrent PPO agent · POPGym Noisy Stateless CartPole HardMMER: 0.27 -> 0.28No clear effect
replace GRU with S5recurrent PPO agent · POPGym runtimespeedupImproved
replace GRU with S5 on randomly-projected StatelessCartPole meta-RLRL2 agent · Randomly-projected StatelessCartPolereturn and runtimeImproved
replace LSTM with S5Muesli meta-RL agent · Multi-environment DMControl meta-RL (train)returnImproved

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