AI Paper Atlas

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

Control Regularization for Reduced Variance Reinforcement Learning

Richard Cheng, Abhinav Verma, Gabor Orosz, Swarat Chaudhuri, Yisong Yue, Joel Burdick

ICML 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 39 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
Mix the policy-gradient controller with a control priorDDPG · CartPole-v1rewardImproved
Mix the policy-gradient controller with a control priorDDPG · Car-followingrewardImproved
Mix the policy-gradient controller with a control priorDDPG · TORCS CG-Speedwaylap-time improvement over control priorImproved
Use adaptive regularization weight based on TD error (ablation)CORE-RL with DDPG · CartPole-v1reward varianceImproved
Use an intermediate fixed regularization weight (ablation)CORE-RL with DDPG · CartPole-v1rewardImproved
Increase regularization weight to a high value (ablation)CORE-RL with DDPG · CartPole-v1rewardHurt
Use a low regularization weight (ablation)CORE-RL with DDPG · CartPole-v1reward varianceHurt
Use an intermediate fixed regularization weight (ablation)CORE-RL with DDPG · Car-followingrewardImproved
Use a low regularization weight (ablation)CORE-RL with DDPG · Car-followingrewardHurt
Use a high regularization weight (ablation)CORE-RL with DDPG · Car-followingrewardHurt
Use adaptive regularization weight based on TD error (ablation)CORE-RL with DDPG · TORCS CG-Speedwaylap-time improvement over control priorImproved
Optimize directly with the regularized loss instead of using policy mixing (ablation)CORE-RL · CartPole-v1rewardHurt

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