Marek Cygan

5

Papers

18

Total Citations

Papers (5)

Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners

Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning

Scaling Laws for Fine-Grained Mixture of Experts

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning