AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Overcoming The Spectral Bias of Neural Value Approximation

Ge Yang, Anurag Ajay, Pulkit Agrawal

ICLR 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 1 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
Replace the MLP value approximator with FFNValue approximation on the Toy MDP · Toy MDPepochs to fit: 2000 -> 400Improved
Use a 12-layer MLP instead of the 4-layer MLP (ablation)Supervised value approximation on the Toy MDP · Toy MDPfit qualityNo clear effect
Train the 4-layer MLP for 2000 rather than 400 epochs (ablation)Value approximation on the Toy MDP · Toy MDPfit quality: 400 epochs -> 2000Improved
Use FFN for the critic while retaining an MLP actor (ablation)SAC · DeepMind Control Suitelearning performanceImproved
Use FFN only for the actor and retain an MLP critic (ablation)SAC · DeepMind Control Suitelearning performanceNo clear effect
Reduce the Fourier feature-to-input ratio below 40 (ablation)FFN with SAC · Quadruped-runlearning performanceHurt
Vary the bandwidth parameter (ablation)FFN with SAC · Walker-run and Quadruped-runlearning performanceMixed
Remove the target network (ablation)FFN with SAC · Finger-turn and Quadruped-walklearning performanceNo clear effect
Remove the target network (ablation)FFN with SAC · Cheetah-run, Walker-run, and Quadruped-runlearning performanceHurt
Remove the target network (ablation)MLP with SAC · DeepMind Control Suitelearning performanceHurt
Increase the replay ratio (ablation)MLP with SAC · Quadruped-runlearning stabilityHurt
Increase the replay ratio (ablation)MLP with SAC · Walker-runlearning performanceImproved

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