-
![]()
Dec 6th 2020
Research Post
Escaping the Gravitational Pull of Softmax
Read more -
![]()
Dec 6th 2020
Research Post
Variational Policy Gradient Method for Reinforcement Learning with General Utilities
Read more -
![]()
Nov 30th 2020
News
Amii accepted papers, workshops & tutorials at NeurIPS 2020
Amii is proud to share the efforts and achievements of our researchers at the 34th Conference on Neural Information Processing Systems (NeurIPS), running online this year Dec 6 - 12.
Read more -
![]()
Nov 11th 2020
Research Post
Asymptotically Optimal Information-Directed Sampling
Read more -
![]()
Nov 8th 2020
Research Post
Online Sparse Reinforcement Learning
Read more -
![]()
Nov 8th 2020
Research Post
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
Read more -
![]()
Oct 31st 2020
Research Post
On Optimality of Meta-Learning in Fixed-Design Regression with Weighted Biased Regularization
Read more -
![]()
Oct 3rd 2020
Research Post
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions
Read more -
![]()
Aug 14th 2020
News
Recommended Reading: How computers beat us at our own games
Popular Science recently shone a light on game-playing AI, as well as Amii researchers' contributions, in their article "How computers beat us at our own games".
Read more -
![]()
Aug 6th 2020
Research Post
BubbleRank: Safe online learning to re-rank via implicit click feedback
Read more -
![]()
Jul 25th 2020
Research Post
Tighter risk certificates for neural networks
Read more -
![]()
Jul 15th 2020
Research Post
Exploration by optimisation in partial monitoring
Read more -
![]()
Jul 13th 2020
News
Amii at ICML 2020: 17 Papers Accepted at Premier ML Conference
Amii is proud to feature the work of our researchers at the 37th International Conference on Machine Learning (ICML).
Read more -
![]()
Jul 13th 2020
Research Post
A simpler approach to accelerated optimization: iterative averaging meets optimism
Read more -
![]()
Jul 12th 2020
Research Post
Model-Based Reinforcement Learning with Value-Targeted Regression
Read more -
![]()
Jun 30th 2020
Research Post
Bandit Algorithms
Read more -
![]()
Jun 23rd 2020
News
The Tea Time Talks 2020: Week One
Watch week one videos of the 2020 Tea Time Talks, featuring Rich Sutton, Csaba Szepesvári, Patrick Pilarski & Martha White.
Read more -
![]()
Jun 18th 2020
Research Post
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting
Read more -
![]()
Jun 9th 2020
Research Post
Differentiable Meta-Learning in Contextual Bandits
Read more -
![]()
Jun 3rd 2020
Research Post
Adaptive Exploration in Linear Contextual Bandit
Read more -
![]()
Jun 3rd 2020
Research Post
Randomized Exploration in Generalized Linear Bandits
Read more -
![]()
May 13th 2020
Research Post
On the Global Convergence Rates of Softmax Policy Gradient Methods
Read more -
![]()
Apr 22nd 2020
News
RL Theory Seminars: bringing theory to the forefront
Amii Fellow and Canada CIFAR AI Chair Csaba Szepesvári has teamed up other researchers to launch the RL Theory Seminar series, a series of online talks geared at increasing knowledge-sharing in the rapidly growing field of reinforcement learning.
Read more -
![]()
Feb 19th 2020
Research Post
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
Read more
