Reinforcement Learning (RL) Reading Club
Abstract
Reinforcement Learning (RL) Reading Club is a seminar series held by Aalto University. The reading club aims to gather people from different fields of science with interest in reinforcement learning.
Seminars are held bi-weekly on Fridays at 11 am to 12 pm. Due to the pandemic situation, all seminars will be organised remotely via Zoom until further notice. Further information will be provided via the club’s mailing list.
Date
Jan 1, 2022 — Dec 31, 2022
Location
Zoom
Click here if you want to join the club’s mailing list!
Talks 2022
| Time | Speaker(s) | Title(s) | Location | Video |
|---|---|---|---|---|
| Fri 28.01.2022 11 am - 12 pm | Yi Zhao | Learning robust perceptive locomotion for quadrupedal robots in the wild | Zoom | Youtube |
| Fri 11.02.2022 11 am - 12 pm | Wenshuai Zhao | Social influence as intrinsic motivation for multi-agent deep reinforcement learning | Zoom | Youtube |
| Fri 25.02.2022 11 am - 12 pm | Nikita Kostin | Learning and Planning in Complex Action Spaces | Zoom | Youtube |
| Fri 11.03.2022 11 am - 12 pm | Maxim Smirnov | Memory-Augmented Dynamic Neural Relational Inference | Zoom | Youtube |
| Fri 25.03.2022 11 am - 12 pm | Pascal Klink | Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning | Zoom | Youtube |
| Fri 08.04.2022 11 am - 12 pm | Noshaba Cheema | Collaborating with Humans without Human Data | Zoom | Youtube |
| Fri 06.05.2022 11 am - 12 pm | Mohammadreza Nakhaei | Decision Transformer: Reinforcement Learning via Sequence Modeling | Zoom | Youtube |
| July - August 2022 | N/A | Summer Break | N/A | N/A |
| Fri 09.09.2022 11 am - 12 pm | Nikita Kostin | Constrained Policy Optimization via Bayesian World Models | Zoom | Youtube |
| Fri 23.09.2022 11 am - 12 pm | Aidan Scannell | Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective | Zoom | TBD |
| Fri 07.10.2022 11 am - 12 pm | TBD | TBD | Zoom | TBD |
| Fri 21.10.2022 11 am - 12 pm | Yuying Zhang | TBD | Zoom | TBD |
| Fri 04.11.2022 11 am - 12 pm | TBD | TBD | Zoom | TBD |
| Fri 18.11.2022 11 am - 12 pm | TBD | TBD | Zoom | TBD |
| Fri 02.12.2022 11 am - 12 pm | TBD | TBD | Zoom | TBD |
| Fri 16.12.2022 11 am - 12 pm | TBD | TBD | Zoom | TBD |
| Stay tuned for more talks. |
Talks 2021
| Time | Speaker(s) | Title(s) | Location | Video |
|---|---|---|---|---|
| Fri 08.10.2021 2 pm - 3 pm | Amin Babadi | Control Strategies for Physically Simulated Characters Performing Two-player Competitive Sports | Zoom | N/A |
| Fri 22.10.2021 2 pm - 3 pm | Reza Taheri | Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning | Zoom | N/A |
Fri 26.11.2021 4 pm - 5 pm | Tuan Dam | Twice Regularized MDPs and the Equivalence Between Robustness and Regularization | Zoom | Youtube |
| Fri 03.12.2021 2 pm - 3 pm | Mohammadreza Nakhaei | Improved Learning of Robot Manipulation Tasks Via Tactile Intrinsic Motivation | Zoom | Youtube |
| Fri 10.12.2021 2 pm - 3 pm | Riad Akrour | Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning | Zoom | Youtube |
| Fri 17.12.2021 2 pm - 3 pm | Nam Hee Gordon Kim | SuperTrack – Motion Tracking for Physically Simulated Characters using Supervised Learning | Zoom | Youtube |