Some highlights from ICLR 2018:
- Our paper on Continuous Adaptation via Meta-Learning (joint work with Trapit, Yura, Ilya, Igor, Pieter at OpenAI) received a Best Paper Award! Check out: poster, talk (starts around 1:20:50).
- We presented DiCE: The Infinitely Differentiable Monte-Carlo Estimator at the workshop. Here is the poster. Reach out if you have questions!