Excited to be at RLC this week in! We will be presenting at the poster sessions for RL Beyond Rewards Workshop tomorrow. Come by to see our work on representation learning and (combinatorial) generalization for goal-conditioned (BC) policies!

Unbelievable that this is the loss we are optimizing for "intelligence".

👍🔥

Really? Is it already too late?

Very nice work at ACM SIGGRAPH that ML researchers should monitor more closely, especially in the areas of image and video generation.

Learning from vision to perform a task is difficult; the agent must solve perception and planning. This work by my student Alexander uses a careful combination of efficient pretrained VLMs to produce object-like embeddings to improve RL policy training speed and robustness.

Great meeting you and Mark Carney at Mila - Institut québécois d'IA. I hope you enjoyed the demo and the fastest explanation of deterministic policy gradients I have ever given. Reach out if you have any questions!

My lab with REAL - Robotics and Embodied AI Lab was honoured to present our recent research and explain how machine learning enables robotics that will drive innovation in Canada. It was a pleasure getting into the details!

Thanks again for the visit PM Mark Carney. We were honoured to show how capable AI is getting on robotics.