Siddhant Agarwal

I am a second year Ph.D. student in the Computer Science Department at University of Texas at Austin, working with Prof. Amy Zhang and Prof. Peter Stone. I completed my Dual Degree (B.Tech. + M.Tech.) in Computer Science and Engineering from the Indian Institute of Technology Kharagpur with a department rank 1. My research interests include goal conditioned reinforcement learning and representation learning. I like to view reinforcement learning from state-visitation distributions perspective and look to extend RL as a distribution matching problem. I am also interested in principled algoritms for learning state abstractions or representations that are useful for unknown downstream tasks.

Google Scholar / Github / Twitter / LinkedIn/ Email / Resume

profile photo
News
Publications
f-Policy Gradients: A General Framework for Goal Conditioned RL using f-Divergences
Siddhant Agarwal, Ishan Durugkar, Peter Stone, Amy Zhang
NeurIPS 2023
project page / arXiv / code

We introduce a general framework for goal conditioned RL using f-divergences.

Behavior Predictive Representations for Generalization in Reinforcement Learning
Siddhant Agarwal, Aaron Courville, Rishabh Agarwal
NeurIPS 2021 workshop on Deep Reinforcement Learning and Ecological Theory of RL
project page / paper /

We introduce latent representations that can predict the behavior of the agent at future steps to improve generalization in RL.

Reinforcement Explanation Learning
Siddhant Agarwal, Owais Iqbal, Sree Aditya Buridi, Mada Manjusha, Abir Das
NeurIPS 2021 workshop on eXplainable AI approaches for debugging and diagnosis
project page / arXiv / code

We reformulate the process of generating saliency maps using perturbation based methods for black box models as a Markov Decsion Process and use RL to optimally search for the best saliency map, thereby reducing the inference time without hurting the performance.

Poisoned Classifiers are not only backdoored, they are fundamentally broken
Minjie Sun, Siddhant Agarwal, Zico Kolter
ICLR 2021 workshop on Security and Safety in Machine Learning systems.
project page / arXiv / code

We show that backdoored classifiers can be attacked by anyone rather than only the adversary. We propose an attack that generates alternate triggers for the poisoned classifiers.

Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbations
Mrigank Raman, Aaron Chan*, Siddhant Agarwal*, Peifeng Wang, Hansen Wang, Sungchul Kim, Ryan Rossi, Handong Zhao, Nedim Lipka, Xiang Ren
* denotes equal contribution
International Conference of Learned Representations 2021 and NeurIPS 2020 workshop on Knowledge Representation and Reasoning in Machine Learning [Best paper nomination]
project page / arXiv / code

We show that using reinforcement learning (or even simple heuristics) we can produce deceptively perturbed knowledge graphs that preserve the downstream performance of the kg-aumented models.

Traffic Sign Classification using HOG-SURF features and Convolutional Neural Networks
Rishabh Madan*, Deepank Agrawal*, Shreyas Kowshik*, Harsh Maheshwari*, Siddhant Agarwal*, Debashish Chakravarty
International Conference on Pattern Recognition Application and Methods, Prague, 2019
project page / paper /

We use a hybrid CNN archticture that uses two image processing features to classify the images. The CNN architecture has significantly less number of parameters than any of the state of the art methods on GTSRB.

Projects
Autonomous Ground Vehicles Research Group IIT Kharagpur
project page /

We worked to develop vision, planning and localization modules for a category 4 autonomous vehicle.

Cluster Management System Distribution Systems Project
project page / report / code

We investigate commonly used cluster management systems like SLURM and Condor. We further develop a fault-tolerant active-passive SLURM-like cluster management system.

Accelerating Graph Algorithms using GPU CUDA Programming Project
project page / report / code

We use parallization in a GPU to accelarate graph algorithms like BFS, DFS and Single Source Shortest Path and All Pair Shortest Path to achieve massive speedups.

Just A Rather Very Interesting Chatbot Software Engineering Project
project page / presentation / code

We develop an android chatbot application using a trained LSTM based encoder-decoder module trained for emotion specific chats. We use a simple classifier to choose the appropriate model from the chat.


Webpage template courtesy: Jon Barron