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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Mix the policy-gradient controller with a control prior | DDPG · CartPole-v1 | reward | Improved |
| Mix the policy-gradient controller with a control prior | DDPG · Car-following | reward | Improved |
| Mix the policy-gradient controller with a control prior | DDPG · TORCS CG-Speedway | lap-time improvement over control prior | Improved |
| Use adaptive regularization weight based on TD error (ablation) | CORE-RL with DDPG · CartPole-v1 | reward variance | Improved |
| Use an intermediate fixed regularization weight (ablation) | CORE-RL with DDPG · CartPole-v1 | reward | Improved |
| Increase regularization weight to a high value (ablation) | CORE-RL with DDPG · CartPole-v1 | reward | Hurt |
| Use a low regularization weight (ablation) | CORE-RL with DDPG · CartPole-v1 | reward variance | Hurt |
| Use an intermediate fixed regularization weight (ablation) | CORE-RL with DDPG · Car-following | reward | Improved |
| Use a low regularization weight (ablation) | CORE-RL with DDPG · Car-following | reward | Hurt |
| Use a high regularization weight (ablation) | CORE-RL with DDPG · Car-following | reward | Hurt |
| Use adaptive regularization weight based on TD error (ablation) | CORE-RL with DDPG · TORCS CG-Speedway | lap-time improvement over control prior | Improved |
| Optimize directly with the regularized loss instead of using policy mixing (ablation) | CORE-RL · CartPole-v1 | reward | Hurt |
Closest papers by meaning
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL (ICML 2025 · similarity 0.89)
- Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning (ICML 2025 · similarity 0.89)
- Decoupling regularization from the action space (ICLR 2024 · similarity 0.88)
- Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning (ICML 2024 · similarity 0.88)
- State Entropy Regularization for Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
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.
