Who am I?
I am a SOTA neural network.
- I have been training in a continual learning setting for more than two decades.
- In 2019, I did rapid domain adaptation to the OOD environment of Berkeley grad school.
- I have successfully learned collaboration in the multi-agent environment of BAIR (Berkeley AI Research).
- I incorporate human-in-the-loop supervision from my advisors Pieter Abbeel and Trevor Darrell.
- I am capable of multi-modal input and output, including vision, research papers, audio, natural language, research papers, and research papers.
- I’m robust against all adversarial inputs except chocolate.
- I achieve near-human performance on all Atari games.
- Approach is not replicable; has only been run on one seed.
- There are serious privacy concerns with the online data collection method, which includes substantial personally identifying information.
- Algorithm may incorporate human biases.
- Source code has been released but is unintelligible; uses only four variable names (ATCG)
- Couldn’t you just use a tranformer for this?
What are my research interests?
The research question I’m most excited about is how to enable humans to teach robots tasks with efficient, natural, low-effort supervision. More concretely, I’m enthusiastic about human-in-the-loop teaching for robotics and unsupervised representation learning methods which will enable robots to learn representations from large-scale data which can make task-specific human supervision downstream more efficient.
Do you have a life outside of research?
In my spare time I play Quidditch, hang out with friends, make mediocre puns, and procrastinate on keeping my website up to date.
- NeurIPSTeachable Reinforcement Learning via Advice DistillationNeurIPS 2021 2021
- ICRAAuto-Tuned Sim-to-Real TransferICRA 2021
- ICML WorkshopExplaining Reinforcement Learning Policies through Counterfactual TrajectoriesICML Workshop on Human in the Loop Learning 2021
- ICNLPHierarchical text generation using an outlineInternational Conference on Natural Language Processing 2018
- ICML WorkshopProgram language translation using a grammar-driven tree-to-tree modelICML Workshop on Neural Abstract Machines & Program Induction 2018