Research map / Reinforcement learning / Policy gradient and actor-critic
Smoothed Action Value Functions for Learning Gaussian Policies
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 a Gaussian policy that learns both its mean and covariance through smoothed action values | Smoothie versus DDPG · Swimmer | average reward | Helped |
| Use a Gaussian policy that learns both its mean and covariance through smoothed action values | Smoothie versus DDPG · Ant | average reward | Helped |
| Use a Gaussian policy that learns both its mean and covariance through smoothed action values | Smoothie versus DDPG · Hopper | average reward: doubled | Helped |
| Use a Gaussian policy that learns both its mean and covariance through smoothed action values | Smoothie versus DDPG · Walker2d | average reward | Helped |
| Use a Gaussian policy that learns both its mean and covariance through smoothed action values | Smoothie versus DDPG · Humanoid | average reward | Helped |
| Add a KL penalty from the previous policy (ablation) | Smoothie · Hopper | average reward | Helped |
| Add a KL penalty from the previous policy (ablation) | Smoothie · Humanoid | average reward | Helped |
| Use a smoothed rather than an ordinary action value to guide policy updates | Smoothie on the synthetic two-Gaussian reward task · Synthetic task | reward | Helped |
Closest papers by meaning
- Stochastic Q-learning for Large Discrete Action Spaces (ICML 2024 · similarity 0.89)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · similarity 0.89)
- Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- Actor-Free Continuous Control via Structurally Maximizable Q-Functions (NeurIPS 2025 · similarity 0.89)
- Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities (NeurIPS 2026 · similarity 0.88)
- Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network (ICML 2025 · similarity 0.87)
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.