AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 9 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
SMERL (diverse near-optimal policies with test-time selection) instead of SAC with 1 policySAC · HalfCheetah-Goal, Walker-Velocity, Hopper-Velocity with obstacle, force, motor failurereturnImproved
Use 5 latent-conditioned policies instead of 1 for SAC (ablation)SAC · Perturbed test environments (except HalfCheetah-Goal + Obstacle)returnImproved
Add diversity reward only when return is near-optimal (SMERL) instead of naively summing DIAYN and task rewards (SAC+DIAYN) (ablation)SAC+DIAYN · Perturbed test environmentsreturnMixed
Add task reward to DIAYN (SMERL instead of DIAYN alone) (ablation)DIAYN · Perturbed test environmentsreturnImproved
Use SMERL instead of adversarial RARL (single policy)RARL · Perturbed test environmentsreturnImproved
Choose best of 5 SMERL policies at test time versus the best training-time policy (ablation)SMERL · HalfCheetah-Goal + Force, magnitude 300.0return: -424.1 (policy 5) -> -222.7 (policy 1)Improved

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