AI Paper Atlas

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

Functional Regularization for Reinforcement Learning via Learned Fourier Features

Alexander Cong Li, Deepak Pathak

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 0 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 MLP with LFF architectureSAC · DMControl state-based (8 envs)return / sample efficiency: better in 6 out of 8 environments, slightly better in the remaining 2Improved
replace CNN with CNN+LFFSAC + RAD · DMControl pixels (4 envs)sample efficiencyImproved
add LFF to PPO policy and criticPPO · OpenAI Gym (4 envs)sample efficiencyNo clear effect
use LFF for only the criticPPO · OpenAI Gym (4 envs)returnMixed
use LFF only for Q-network (ablation)SAC · Walker, QuadrupedreturnImproved
use LFF only for policy network (ablation)SAC · Walker, QuadrupedreturnNo clear effect
fix Fourier basis B instead of training it (ablation)LFF · DMControl 4 envsreturnHurt
remove input concatenation (ablation)LFF · Quadruped, HumanoidreturnHurt
remove input concatenation (ablation)LFF · Walker, FingerreturnNo clear effect
use log-uniform initialization of B instead of N(0, sigma^2) (ablation)LFF · DMControlreturnHurt
concatenate input x to MLP first layer output (ablation)MLP · state-based DMControlreturnNo clear effect
remove target networkSAC with LFF vs MLP · DMControl state-basedreturnImproved

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