PhD student @rlai_lab. Prev: @GoogleDeepMind, @OcadoTechnology, @kindredai, @UofTCompSci
Edmonton
Joined October 2020
- Tweets52
- Following544
- Followers195
- Likes4.1K
Why do we assume an RL agent can always compute the correct action immediately? Every policy is a program and thus resource bounded. In this blog, I argue why computation should be part of decision making, illustrated with some toy examples.
🔗chanb.github.io/blogs/necess…
I will be presenting this paper on how models trade-off in-context and in-weight learning at #ICLR2025
Drop by on Saturday and I’ll be happy to chat!
Excited to share that our work on understanding when ICL emerges has been accepted to #ICLR2025 !
Submission for preview: openreview.net/forum?id=aKJr…
Bryan Chan retweeted
Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD
Excited to share that our work on understanding when ICL emerges has been accepted to #ICLR2025 !
Submission for preview: openreview.net/forum?id=aKJr…
Thanks @m_wulfmeier ! We were surprised to see that SAC-X is just very robust. Something that was interesting to us that we didn’t further investigate: Learning from examples ended up being more efficient than using reward. Let’s chat at #NeurIPS2024 if there’s a chance?
Here's a fascinating paper by @domo_mr_roboto's group linking hierarchical reinforcement learning and cheaply-obtainable auxiliary tasks arxiv.org/abs/2407.03311
Better exploration with minimal engineering effort remains a critical challenge (even for RLHF/AIF) - reminiscent of our efforts on SAC-X and intrinsic rewards through representation learning (VAE, Transporter, etc.) arxiv.org/abs/2011.01758
Excited to see more progress in this space!
#robotics #reinforcementlearning
Bryan Chan retweeted
Would you believe that deep RL can work without replay buffers, target networks, or batch updates? Our recent work gets deep RL agents to learn from a continuous stream of data one sample at a time without storing any sample. Joint work with @Gautham529 and @rupammahmood.
Bryan Chan retweeted
Our NeurIPS paper is now on arXiv:
We introduce Action Value Gradient (AVG), a novel incremental deep RL method that learns in real-time, one sample at a time — no batch updates, target networks or a replay buffer!
Co-authors @mhmd_elsaye @bellingerc @white_martha @rupammahmood
Bryan Chan retweeted
Hey all! We are thrilled to have @chanpyb from @UAlberta for this week's seminar! The talk is titled: "Why can't we use reinforcement learning for
image-based robotic manipulation?". See you at 11:30AM ET!
youtube.com/@MontrealRobotic…
#rl #manipulation, #imitationLearning
LLMs can leverage context information, i.e., in-context learning (ICL) or memorize solutions, i.e., in-weight learning (IWL) for prediction, but when do they happen? 1/N
Of course, we have also conducted experiments on a synthetic dataset, Omniglot, and fine-tuned a LLM with a small number of prompts to corroborate our theoretical findings. 7/N
I think this line of work will lead us to a better understanding of how LLMs work and further lead us to new ideas in designing training algorithms for various LLMs. N/N
Arxiv Link: arxiv.org/abs/2410.23042
It's been bugging me how we only use imitation learning for robot learning and just scale number of demonstrations. In our latest work @OcadoTechnology we propose a offline-to-online #RL algorithm to do robotic grasp in real life!
arxiv.org/abs/2410.14957 1/N
Finally, what's cool about this is that we actually compared these algorithms over multiple seeds, which many papers don't do when it comes to real-life robotic experiments! 7/N
I think this line of work is very promising, many theoretical questions to answer. We also bypassed exploration for now with the demonstrations.
Credits to my collaborators Anson Leung and @jabergT. N/N