Kamyar Azizzadenesheli

verfied profile

∙ 0 followers
University of California, Irvine

Learning Causal State Representations of Partially Observable Environments

Intelligent agents can cope with sensory-rich environments by learning t...
06/25/2019 ∙ by Amy Zhang, et al. ∙ 68 ∙ share

read it
Stochastic Linear Bandits with Hidden Low Rank Structure

High-dimensional representations often have a lower dimensional underlyi...
01/28/2019 ∙ by Sahin Lale, et al. ∙ 18 ∙ share

read it
Regret Minimization in Partially Observable Linear Quadratic Control

We study the problem of regret minimization in partially observable line...
01/31/2020 ∙ by Sahin Lale, et al. ∙ 13 ∙ share

read it
Sample-Efficient Deep RL with Generative Adversarial Tree Search

We propose Generative Adversarial Tree Search (GATS), a sample-efficient...
06/15/2018 ∙ by Kamyar Azizzadenesheli, et al. ∙ 4 ∙ share

read it
Experimental results : Reinforcement Learning of POMDPs using Spectral Methods

We propose a new reinforcement learning algorithm for partially observab...
05/07/2017 ∙ by Kamyar Azizzadenesheli, et al. ∙ 0 ∙ share

read it
Reinforcement Learning in Rich-Observation MDPs using Spectral Methods

Designing effective exploration-exploitation algorithms in Markov decisi...
11/11/2016 ∙ by Kamyar Azizzadenesheli, et al. ∙ 0 ∙ share

read it
Reinforcement Learning of POMDPs using Spectral Methods

We propose a new reinforcement learning algorithm for partially observab...
02/25/2016 ∙ by Kamyar Azizzadenesheli, et al. ∙ 0 ∙ share

read it
Efficient Exploration through Bayesian Deep Q-Networks

We propose Bayesian Deep Q-Network (BDQN), a practical Thompson sampling...
02/13/2018 ∙ by Kamyar Azizzadenesheli, et al. ∙ 0 ∙ share

read it
Stochastic Activation Pruning for Robust Adversarial Defense

Neural networks are known to be vulnerable to adversarial examples. Care...
03/05/2018 ∙ by Guneet S. Dhillon, et al. ∙ 0 ∙ share

read it
signSGD: compressed optimisation for non-convex problems

Training large neural networks requires distributing learning across mul...
02/13/2018 ∙ by Jeremy Bernstein, et al. ∙ 0 ∙ share

read it
signSGD with Majority Vote is Communication Efficient And Byzantine Fault Tolerant

Training neural networks on large datasets can be accelerated by distrib...
10/11/2018 ∙ by Jeremy Bernstein, et al. ∙ 0 ∙ share

read it
Trust Region Policy Optimization of POMDPs

We propose Generalized Trust Region Policy Optimization (GTRPO), a Reinf...
10/18/2018 ∙ by Kamyar Azizzadenesheli, et al. ∙ 0 ∙ share

read it
Neural Lander: Stable Drone Landing Control using Learned Dynamics

Precise trajectory control near ground is difficult for multi-rotor dron...
11/19/2018 ∙ by Guanya Shi, et al. ∙ 0 ∙ share

read it
Regularized Learning for Domain Adaptation under Label Shifts

We propose Regularized Learning under Label shifts (RLLS), a principled ...
03/22/2019 ∙ by Kamyar Azizzadenesheli, et al. ∙ 0 ∙ share

read it
Directivity Modes of Earthquake Populations with Unsupervised Learning

We present a novel approach for resolving modes of rupture directivity i...
06/30/2019 ∙ by Zachary E. Ross, et al. ∙ 0 ∙ share

read it

Kamyar Azizzadenesheli

Featured Co-authors

Anima Anandkumar

Joelle Pineau

Zachary C Lipton

Yisong Yue

Emma Brunskill

Alessandro Lazaric

Yu-Xiang Wang

Babak Hassibi

Jean Kossaifi

Laurent Itti

Rose Yu

Learning Causal State Representations of Partially Observable Environments

Stochastic Linear Bandits with Hidden Low Rank Structure

Regret Minimization in Partially Observable Linear Quadratic Control

Sample-Efficient Deep RL with Generative Adversarial Tree Search

Experimental results : Reinforcement Learning of POMDPs using Spectral Methods

Reinforcement Learning in Rich-Observation MDPs using Spectral Methods

Reinforcement Learning of POMDPs using Spectral Methods

Efficient Exploration through Bayesian Deep Q-Networks

Stochastic Activation Pruning for Robust Adversarial Defense

signSGD: compressed optimisation for non-convex problems

signSGD with Majority Vote is Communication Efficient And Byzantine Fault Tolerant

Trust Region Policy Optimization of POMDPs

Neural Lander: Stable Drone Landing Control using Learned Dynamics

Regularized Learning for Domain Adaptation under Label Shifts

Directivity Modes of Earthquake Populations with Unsupervised Learning