AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Zap Q-Learning With Nonlinear Function Approximation

Shuhang Chen, Adithya M Devraj, Fan Lu, Ana Busic, Sean Meyn

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Neural network approximation theory · 8 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
Update the gain periodically with N_d=50 instead of every iteration (ablation)Zap Q-learning · Mountain Car, Acrobot, and CartpoleperformanceNo clear effect
Include the term D(θ_n, Φ_{n+1})∂_θζ_n when computing A_{n+1} (ablation)Zap Q-learning with periodic eligibility updates · OpenAI Gym examplesperformanceNo clear effect
Use constant rather than decreasing step sizes (ablation)Zap Q-learning · Mountain Car and Acrobotaverage rewardImproved
Use decreasing rather than constant step sizes (ablation)Zap Q-learning · Cartpoleaverage rewardImproved

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