↓Skip to main content

🏢 University of Alberta

Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark
·2138 words·11 mins· loading · loading
AI Generated Computer Vision Image Segmentation 🏢 University of Alberta
New MVUAV dataset and SemiMV semi-supervised learning model significantly improve multispectral video semantic segmentation!
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q^π-Realizability and Concentrability
·479 words·3 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 University of Alberta
Offline RL with trajectory data achieves statistically efficient learning under linear q*-realizability and concentrability, solving a previously deemed impossible problem.
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
·3400 words·16 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 University of Alberta
Recurrent Trace Units (RTUs) significantly enhance real-time recurrent learning in reinforcement learning, outperforming other methods with less computation.
Learning Truncated Causal History Model for Video Restoration
·2473 words·12 mins· loading · loading
Computer Vision Video Understanding 🏢 University of Alberta
TURTLE: a novel video restoration framework that learns a truncated causal history model for efficient and high-performing video restoration, achieving state-of-the-art results on various benchmark ta…
Distributional Reinforcement Learning with Regularized Wasserstein Loss
·2196 words·11 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 University of Alberta
Sinkhorn distributional RL (SinkhornDRL) uses a regularized Wasserstein loss to improve distributional reinforcement learning.
Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers
·3268 words·16 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 University of Alberta
Deep RL excels in simulated robotics, but struggles with real-world limitations like limited computational resources. This paper introduces Action Value Gradient (AVG), a novel incremental deep polic…
Confident Natural Policy Gradient for Local Planning in q_π-realizable Constrained MDPs
·227 words·2 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 University of Alberta
Confident-NPG-CMDP: First primal-dual algorithm achieving polynomial sample complexity for solving constrained Markov decision processes (CMDPs) using function approximation and local access model.
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
·359 words·2 mins· loading · loading
AI Theory Optimization 🏢 University of Alberta
Generalized linear bandits with subexponential reward distributions are self-concordant, enabling second-order regret bounds free of exponential dependence on problem parameters.
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
·1860 words·9 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 University of Alberta
New empirical methodology quantifies how much reinforcement learning algorithm performance relies on per-environment hyperparameter tuning, enabling better algorithm design.