Aviral Kumar

6 papers Carnegie Mellon University

• Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
• Compute-Optimal Scaling for Value-Based Deep RL
• Grounded Reinforcement Learning for Visual Reasoning
• Horizon Reduction Makes RL Scalable
• Reasoning as an Adaptive Defense for Safety
• Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction