Research map / Reinforcement learning / MDPs and planning
A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning
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 Cos instead of the other tested regularizers | RAC · Alien | score | Helped |
| Use Cos instead of the other tested regularizers | RAC · Seaquest | score | Helped |
| Use Tsallis instead of the other tested regularizers | RAC · Boxing | score | Helped |
| Use Shannon instead of the other tested regularizers | RAC · Atari tasks other than Breakout | score | Hurt |
| Use Tsallis instead of Shannon at the same regularization coefficient | RAC · MuJoCo continuous control tasks | average return | Helped |
| Use Tsallis instead of Shannon | RAC · MuJoCo continuous control tasks | training stability | Helped |
| Use Exp instead of Tsallis | RAC · Ant-v2 and Hopper-v2 | average return | No clear effect |
| Use Exp instead of Tsallis | RAC · The other two MuJoCo environments | average return | Hurt |
| Use Cos regularization in continuous-control training | RAC · MuJoCo continuous control tasks | training stability | Hurt |
| Use Tsallis instead of Cos or Shannon | RAC · MuJoCo continuous control tasks | sensitivity to λ | Helped |
| Use Shannon instead of the other tested regularizers | RAC · Atari tasks | sensitivity to λ | Helped |
Closest papers by meaning
- Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm (NeurIPS 2025 · similarity 0.88)
- A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach (ICML 2025 · similarity 0.88)
- Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning (ICML 2025 · similarity 0.88)
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.88)
- Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs (NeurIPS 2026 · 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.