Research map / Reinforcement learning / Policy gradient and actor-critic
Efficient Continuous Control with Double Actors and Regularized Critics
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use double actors, double critics, soft value targets, and critic regularization (DARC) | TD3-style continuous-control agents · Ant | final score: DATD3: 5180.29; DARC: 5642.33 ± 188.82 | Helped |
| Use DARC | TD3-style continuous-control agents · BipedalWalker | final score: DATD3: 305.09; DARC: 311.25 ± 2.66 | Helped |
| Use DARC | TD3-style continuous-control agents · HalfCheetah | final score: SD3: 10934.72; DARC: 11600.74 ± 499.11 | Helped |
| Use DARC | TD3-style continuous-control agents · Hopper | final score: SD3: 3286.24; DARC: 3577.93 ± 133.97 | Helped |
| Use DARC | TD3-style continuous-control agents · Humanoid | final score: TADD: 6182.54; DARC: 6737.63 ± 743.95 | Helped |
| Use DARC | TD3-style continuous-control agents · Walker2d | final score: DARC: 5045.36 ± 548.12 | Helped |
| Use DARC | TD3-style continuous-control agents · AntPyBullet | final score: DATD3: 3949.02; DARC: 4100.01 ± 19.24 | Helped |
| Use DARC | TD3-style continuous-control agents · W2dPyBullet | final score: DARC: 1902.46 ± 217.25 | Helped |
| Add double-actor value correction (ablation) | DARC · HalfCheetah-v2 | return | Helped |
| Add critic regularization (ablation) | DARC · HalfCheetah-v2 | return | Helped |
| Select actions using the actor with higher expected return (ablation) | DARC · HalfCheetah-v2 | return | Helped |
| Use DARC's regularized critic update rather than CTD3's separate critic updates (ablation) | TD3-style agents · HalfCheetah-v2 | return | Helped |
Closest papers by meaning
- Value Improved Actor Critic Algorithms (NeurIPS 2025 · similarity 0.87)
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL (NeurIPS 2025 · similarity 0.87)
- Actor-Free Continuous Control via Structurally Maximizable Q-Functions (NeurIPS 2025 · similarity 0.87)
- ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages (ICML 2024 · similarity 0.87)
- Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning (ICML 2024 · similarity 0.87)
- Actor-Critics Can Achieve Optimal Sample Efficiency (ICML 2025 · similarity 0.86)
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.