Picture for Javad Lavaei

Javad Lavaei

Max

High Probability Complexity Bounds of Trust-Region Stochastic Sequential Quadratic Programming with Heavy-Tailed Noise

Add code
Mar 24, 2025
Viaarxiv icon

Subgradient Method for System Identification with Non-Smooth Objectives

Add code
Mar 20, 2025
Viaarxiv icon

Reward-Safety Balance in Offline Safe RL via Diffusion Regularization

Add code
Feb 18, 2025
Viaarxiv icon

Exact Recovery Guarantees for Parameterized Non-linear System Identification Problem under Adversarial Attacks

Add code
Aug 30, 2024
Viaarxiv icon

A Black Swan Hypothesis in Markov Decision Process via Irrationality

Add code
Jul 25, 2024
Figure 1 for A Black Swan Hypothesis in Markov Decision Process via Irrationality
Viaarxiv icon

A CMDP-within-online framework for Meta-Safe Reinforcement Learning

Add code
May 26, 2024
Viaarxiv icon

Pausing Policy Learning in Non-stationary Reinforcement Learning

Add code
May 25, 2024
Figure 1 for Pausing Policy Learning in Non-stationary Reinforcement Learning
Figure 2 for Pausing Policy Learning in Non-stationary Reinforcement Learning
Figure 3 for Pausing Policy Learning in Non-stationary Reinforcement Learning
Figure 4 for Pausing Policy Learning in Non-stationary Reinforcement Learning
Viaarxiv icon

Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses

Add code
Mar 10, 2024
Viaarxiv icon

Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing

Add code
Oct 24, 2023
Viaarxiv icon

Tempo Adaption in Non-stationary Reinforcement Learning

Add code
Sep 26, 2023
Viaarxiv icon