-
![]()
Nov 23rd 2022
News
16 papers co-authored by Amii researchers featured at NeurIPS 2022
Amii researchers present their work in the fields of reinforcement learning, natural language processing, data optimization and more at the 2022 Conference on Neural Information Processing Systems.
Read more -
![]()
Nov 30th 2021
News
Bandit tasks, deep reinforcement learning and controlling disinformation: Amii researchers at NeurIPS 2021
Amii is proud to share the work of our researchers that will be presented at the thirty-fifth annual Neural Information Processing Systems (NeurIPS) conference, held online from December 6 - 14, 2021.
Read more -
![]()
Oct 29th 2021
Research Post
Understanding the Effect of Stochasticity in Policy Optimization
Read more -
![]()
Oct 21st 2021
News
Learn about the AI research shaping the future of video games
Will intelligent tutoring agents replace game tutorials? Can AI models assist level designers and still keep the designer’s creative style? Dive into the AI research shaping video games.
Read more -
![]()
Jul 27th 2021
Research Post
On the Role of Optimization in Double Descent: A Least Squares Study
Read more -
![]()
Jul 21st 2021
News
AI in Video Games: Optimization in Reinforcement Learning with Csaba Szepesvári
Video games have long been a domain explored by AI researchers, and researchers from Amii have a rich history producing advancements that can help across all aspects of game design, development and delivery.
Read more -
![]()
Jul 17th 2021
Research Post
No Regrets for Learning the Prior in Bandits
Read more -
![]()
Jul 13th 2021
News
Amii at ICML 2021: Accepted papers & workshops
The work of Amii researchers is being featured at the 38th annual International Conference on Machine Learning (ICML), running online this year from July 18 to 24.
Read more -
![]()
Jul 13th 2021
Research Post
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
Read more -
Jul 13th 2021
Research Post
Meta-Thompson Sampling
Read more -
![]()
Jun 23rd 2021
News
The Tea Time Talks 2021: Week One
Watch this week's videos featuring Richard Sutton, Rupam Mahmood and an RLAI panel! The Tea Time Talks are 20-minute talks on early-stage ideas, prospective research and technical topics.
Read more -
![]()
Jun 4th 2021
Research Post
A Distribution-dependent Analysis of Meta Learning
Read more -
![]()
May 13th 2021
Research Post
Leveraging Non-uniformity in First-order Non-convex Optimization
Read more -
![]()
Apr 6th 2021
Research Post
On the Optimality of Batch Policy Optimization Algorithms
Read more -
![]()
Feb 25th 2021
Research Post
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
Read more -
![]()
Feb 22nd 2021
News
AI Seminar Series 2021: Csaba Szepesvári, Hardness of MDP planning with linear function approximation
On February 19, 2021, Amii Fellow & Canada CIFAR AI Chair Csaba Szepesvári presented "Hardness of MDP planning with linear function approximation".
Read more -
![]()
Dec 15th 2020
Research Post
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
Read more -
![]()
Dec 6th 2020
Research Post
Differentiable Meta-Learning of Bandit Policies
Read more -
![]()
Dec 6th 2020
Research Post
Online Algorithm for Unsupervised Sequential Selection with Contextual Information
Read more -
![]()
Dec 6th 2020
Research Post
Efficient Planning in Large MDPs with Weak Linear Function Approximation
Read more -
![]()
Dec 6th 2020
Research Post
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool
Read more -
![]()
Dec 6th 2020
Research Post
Model Selection in Contextual Stochastic Bandit Problems
Read more -
![]()
Dec 6th 2020
Research Post
PAC-Bayes Analysis Beyond the Usual Bounds
Read more -
![]()
Dec 6th 2020
Research Post
CoinDICE: Off-Policy Confidence Interval Estimation
Read more
