PPaperPicks

Marek Cygan

9 papers at tracked venues · 8 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. A Case for Validation Buffer in Pessimistic Actor-Critic
  2. Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
  3. Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning
  4. FlySearch: Exploring how vision-language models explore
  5. Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
  6. Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
  7. Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
  8. Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
  9. Scaling Laws for Fine-Grained Mixture of Experts