AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

Mengdi Xu, Wenhao Ding, Jiacheng Zhu, ZUXIN LIU, Baiming Chen, Ding Zhao

NeurIPS 2020 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Infinite-width networks as Gaussian processes · 2 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
remove dynamics assignment (single GP) (ablation)Our Method · CartPole Task2mean accumulated reward: 169.46 -> 183.10Improved
remove dynamics assignment (single GP) (ablation)Our Method · CartPole Task1mean accumulated reward: 178.04 -> 177.62No clear effect
remove dynamics assignment (single GP) (ablation)Our Method · HalfCheetah Task1mean accumulated reward: 2.70 -> 36.11Improved
remove dynamics assignment (single GP) (ablation)Our Method · HalfCheetah Task2mean accumulated reward: -21.26 -> 34.14Improved
remove dynamics assignment (single GP) (ablation)Our Method · Intersection Task2mean accumulated reward: 39.23 -> 54.77Improved
remove dynamics assignment (single GP) (ablation)Our Method · Intersection Task3mean accumulated reward: 44.25 -> 52.48Improved
DP prior with DNN (DPNN) instead of transition prior with GPOur Method · CartPole Task4mean accumulated reward: 161.58 -> 182.54Improved
DP prior with DNN (DPNN) instead of transition prior with GPOur Method · CartPole Task1mean accumulated reward: 187.24 -> 177.62Hurt
DP prior with DNN (DPNN) instead of transition prior with GPOur Method · HalfCheetah Task1mean accumulated reward: -42.88 -> 36.11Improved
DP prior with DNN (DPNN) instead of transition prior with GPOur Method · Intersection Task3mean accumulated reward: 18.64 -> 52.48Improved
pre-trained ANP instead of online GP mixtureOur Method · Intersection Task1mean accumulated reward: 62.68 -> 60.66Hurt
online GP mixture instead of pre-trained DNNDNN · CartPole Task1mean accumulated reward: 176.57 -> 177.62No clear effect

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