4 citations · 12 across the 10 of their papers we have counts for
10 papers
RLZero: Direct Policy Inference from Language Without In-Domain Supervision
Harshit Sikchi, Siddhant Agarwal, Pranaya Jajoo +6
The reward hypothesis states that all goals and purposes can be understood as the maximization of a received scalar reward signal. However, in practice, defining such a reward sign…
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
Jake Grigsby, Justin Sasek, Samyak Parajuli +3
Language models trained on diverse datasets unlock generalization by in-context learning. Reinforcement Learning (RL) policies can achieve a similar effect by meta-learning within…
Social Conjuring: Multi-User Runtime Collaboration with AI in Building Virtual 3D Worlds
Amina Kobenova, Cyan DeVeaux, Samyak Parajuli +3
Generative artificial intelligence has shown promise in prompting virtual worlds into existence, yet little attention has been given to understanding how this process unfolds as so…
DreamGarden: A Designer Assistant for Growing Games from a Single Prompt
Sam Earle, Samyak Parajuli, Andrzej Banburski-Fahey
Coding assistants are increasingly leveraged in game design, both generating code and making high-level plans. To what degree can these tools align with developer workflows, and wh…
Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding
Yatong Bai, Utsav Garg, Apaar Shanker +10
Vision and vision-language applications of neural networks, such as image classification and captioning, rely on large-scale annotated datasets that require non-trivial data-collec…
Learning Generalizable Multi-Lane Mixed-Autonomy Behaviors in Single Lane Representations of Traffic
Abdul Rahman Kreidieh, Yibo Zhao, Samyak Parajuli +1
Reinforcement learning techniques can provide substantial insights into the desired behaviors of future autonomous driving systems. By optimizing for societal metrics of traffic su…
Explore and Control with Adversarial Surprise
Arnaud Fickinger, Natasha Jaques, Samyak Parajuli +5
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challen…
Dynamically Throttleable Neural Networks (TNN)
Hengyue Liu, Samyak Parajuli, Jesse Hostetler +2
Conditional computation for Deep Neural Networks (DNNs) reduce overall computational load and improve model accuracy by running a subset of the network. In this work, we present a…
Inter-Level Cooperation in Hierarchical Reinforcement Learning
Abdul Rahman Kreidieh, Glen Berseth, Brandon Trabucco +3
Hierarchies of temporally decoupled policies present a promising approach for enabling structured exploration in complex long-term planning problems. To fully achieve this approach…
Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks
Samyak Parajuli, Aswin Raghavan, Sek Chai
The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations. Ternary Connect (TC) \cite{lin2015neural} addresses…