Mila > The Mila Blog

The Mila Blog

02/06/2023
Generalization properties of biologically-plausible temporal credit assignment rules
by Yuhan Helena Liu
Read article
25/04/2023
Generalized Data Weighting via Class-level Gradient Manipulation
by Can Chen
Read article
04/04/2023
Scaling in the service of reasoning & model-based ML
by Yoshua Bengio, Edward J. Hu
Read article
06/03/2023
Adversarial Deep Reinforcement Learning: Adversarial Attacks Transfers Across MDPs
by Ezgi Korkmaz
Read article
15/02/2023
Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
by Jędrzej Orbik, Charles Sun, Coline Devin, Glen Berseth
Read article
25/11/2022
Beyond Tabula Rasa: Reincarnating Reinforcement Learning
by Max Schwarzer, Rishabh Agarwal
Read article
31/08/2022
Direct Behavior Specification via Constrained Reinforcement Learning
by Julien Roy, Roger Girgis, Joshua Romoff, Pierre-Luc Bacon, Chris Pal
Read article
01/08/2022
AnyMorph: Learning Transferable Policies By Inferring Agent Morphology
by Brandon Trabucco
Read article
13/07/2022
The Primacy Bias in Deep Reinforcement Learning
by Pierluca D'Oro, Evgenii Nikishin
Read article
13/06/2022
Compositional Attention: Disentangling Search and Retrieval
by Sarthak Mittal
Read article
12/05/2022
RLiable: Towards Reliable Evaluation & Reporting in Reinforcement Learning
by Rishabh Agarwal and Pablo Samuel Castro
Read article
09/05/2022
Sample Efficient Deep Reinforcement Learning Via Uncertainty Estimation
by Vincent Mai, Kaustubh Mani and Liam Paull
Read article
23/03/2022
A collaboration between Mila and Relation Therapeutics to discover novel synergistic combinations of drugs in vitro
by Paul Bertin, Jake P. Taylor-King, Yoshua Bengio
SMO out-of-distribution drug development
Read article
17/03/2022
Researchers carry out the largest-ever psychedelics study using natural language processing tools
by Brigitte Tousignant
neurosciences NLP
Read article
15/03/2022
Generative Flow Networks
by Yoshua Bengio
GFlowNets
Read article