Johan Obando Ceron

4 papers Mila / Université de Montréal

• Generating Creative Chess Puzzles
• Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
• Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
• Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training