AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Tempo Adaptation in Non-stationary Reinforcement Learning

Hyunin Lee, Yuhao Ding, Jongmin Lee, Ming Jin, Javad Lavaei, Somayeh Sojoudi

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL

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 ProST-G instead of the strongest baselineSwimmer-v2 · speeds 1–5average return: 0.57 vs -0.08; 1.04 vs 0.20; 1.52 vs -0.13; 2.01 vs -0.04; 2.81 vs 0.10Improved
Use ProST-G instead of MBPOHalfcheetah-v2 · speeds 1–4average return: -19.69 vs -24.89; -20.21 vs -22.19; -21.04 vs -21.65; -19.55 vs -21.40Improved
Use ProST-G instead of MBPOHalfcheetah-v2 · speed 5average return: -20.50 vs -20.52Hurt
Use ProST-G instead of the strongest baselineHopper-v2 · speed 1average return: 92.77 vs 98.38Hurt
Use ProST-G instead of the strongest baselineHopper-v2 · speeds 2–5average return: 98.13 vs 99.02; 100.42 vs 98.60; 100.68 vs 98.89; 102.48 vs 99.64Mixed
Set policy training time to Δπ=4 (ablation)ProST-G · synthetic non-stationary environmentaverage rewardImproved
Replace ARIMA with a simple average forecaster, varying window size w (ablation)ProST-G · four environment speedsaverage rewardMixed
Use a proactive ARIMA forecaster instead of MBPO's reactive model (ablation)ProST-G / MBPO · non-stationary Mujoco tasksaverage rewardImproved
Jointly optimize data weights and the future model with W-LSE instead of selecting a fixed sliding window with SW-LSE (ablation)ProST-T · time-elapsing MDPdynamic regret upper boundImproved

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