Timetable
02.14:Week 0: Kick-off seminar
Introduction, organization of the seminar, questions.
presented by Raul Vicente
feedback | test
02.21:Week 1: One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning presented by Sebastian Värv and Mari Liis Velner
feedback | test
02.28:Week 2: A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
presented by Markus Loide and Martin Liivak
feedback | test
03.07:Week 3: Continuous online sequence learning with an unsupervised neural network model
presented by Vladyslav Fediukov and Anton Potapchuk
feedback | test
03.14: Week 4:Counterfactual Multi-Agent Policy Gradients presented by Novin Shahroudi and Kaur Karus
feedback | test
03.21: Week 5:InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets presented by Marharyta Dekret and Diana Grygorian
feedback | test
03.28: Week 6 Simple random search provides a competitive approach to reinforcement learning presented by Tambet Matiisen.
Survey | Attendance
04.04: Week 7: Searching for Principles of Brain Computation
presented by Sriyal Jayasinghe and Yevheniia Kryvenko
feedback |test
04.11: Week 8:Diversity is All You Need: Learning Skills without a Reward Function presented by Lisa Yankovskaya and Krister Jaanhold
feedback | test
04.18: Week 9:Random synaptic feedback weights support error backpropagation for deep learning presented by Hina Anwar and Martin Valgur
feedback | test
04.25: Week 10 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
presented by Basar Turgut and Prabhant Singh
feedback | test
05.02: Week 11: Emergent Complexity via Multi-Agent Competition presented by Gunay Abdullayeva and Aytaj Aghabayli
feedback | test
05.09: Week 12: Policy Distillation presented by Muhammad Uzair
feedback | test
05.16: Week 13:Efficient inverse graphics in biological face processing presented by Madis Vasser and Mansur Alizada
feedback | test
05.23: Week 14: World Models presented by Aqeel Labash and Daniel Majoral
feedback | test