Schedule
Embedded Files
On the Day
On the Day
Our workshop will be in CCIS 1-440.
09:00 - 09:10 (10 minutes) - Opening Remarks
09:10 - 09:25 (15 minutes) - Invited Talk: Prof. Erin Talvitie (Harvey Mudd).
09:25 - 09:40 (15 minutes) - Invited Talk: Prof. George Konidaris (Brown) - Agents Must Learn Their Own Frames.
09:40 - 09:55 (15 minutes) - Invited Talk: Prof. Mark Ho (NYU).
09:55 - 10:10 (15 minutes) - Invited Talk: Dr. Clare Lyle (Google DeepMind).
10:10 - 10:40 (30 minutes) - Coffee Break
10:40 - 11:40 (1 hour) - Panel Discussion
11:40 - 12:30 (50 minutes) - Poster Session #1
12:30 - 14:00 (1 hour 30 minutes) - Lunch Break
14:00 - 14:45 (45 minutes) - Lightning Talks (~ 13 mins for each talk including its Q&A time)
Thinking is Another Form of Control. Josiah P. Hanna and Nicholas E. Corrado.
Awarded: Most Thought-provoking paper.
Analogy making as amortised model construction. David G Nagy, Tingke Shen, Hanqi Zhou, Charley M Wu, and Peter Dayan.
Agent-centric learning: from external reward maximization to internal knowledge curation. Hanqi Zhou, Fryderyk Mantiuk, David G Nagy, and Charley M Wu.
14:45 - 15:05 (20 minutes) - Tea Break
15:05 - 15:55 (50 minutes) - Poster Session #2
15:55 - 16:05 (10 minutes) - Closing Remarks
I will argue that: 1) the right outer frame for a generally-intelligent agent is a decision process, 2) that that decision process must necessarily be drastically overpowered, compared to the natural framing of any individual task it may wish to solve, and that therefore 3) a critical component for achieving general intelligence is the ability to autonomously construct task-specific frames, which can be achieved by learning mutually-compatible observation and action abstractions. Finally, I will briefly discuss how 4) a reinforcement-learning agent able to do so can access the rest of AI.
Page updated
Google Sites
Report abuse