AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Gradient Temporal-Difference Learning with Regularized Corrections

Sina Ghiassian, Andrew Patterson, Shivam Garg, Dhawal Gupta, Adam White, Martha White

ICML 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 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
Add ℓ2 regularization to the secondary-weight update (TDRC instead of TDC) (ablation)TDRC · Boyan's ChainRMSPBE area: 0.639 ± 0.001 -> 0.222 ± 0.002Improved
Add ℓ2 regularization to the secondary-weight update (TDRC instead of TDC) (ablation)TDRC · Baird's CounterexampleRMSPBE area: 0.196 ± 0.007 -> 0.242 ± 0.006Mixed
Add ℓ2 regularization to the secondary-weight update (TDRC instead of TDC) (ablation)TDRC · Random Walk (Inverted)RMSPBE area: 0.053 ± 0.001 -> 0.047 ± 0.001Improved
Add ℓ2 regularization to the secondary-weight update (TDRC instead of TDC) (ablation)TDRC · Random Walk (Tabular)RMSPBE area: 0.063 ± 0.001 -> 0.049 ± 0.001Mixed
Increase regularization from zero (TDC) to a positive β (ablation)TDRC · Random Walk, Boyan's Chain, and Baird's CounterexampleRMSPBEImproved
Use β = 1.0 rather than the better-performing larger β values identified by tuning (ablation)TDRC · Linear prediction problemsRMSPBEHurt
Reduce the secondary-weights stepsize multiplier to η = 0.5 (ablation)QC · Mountain Car (neural network)steps to goalImproved
Use QC instead of Q-learningQC · MinAtar Breakout and Space Invadersaverage returnImproved
Use QRC with β = 1 instead of QC (ablation)QRC · MinAtar Breakout and Space Invadersaverage returnHurt
Use QRC instead of Q-learningQRC · Mountain Car with 10 replay stepssteps to goalImproved
Add target networks (ablation)Q-learning · Non-linear control environmentslearning performanceHurt
Use momentum with Adam instead of Adagrad (ablation)TDRC and comparison methods · Linear prediction problemsRMSPBENo 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