1 citations · 1 across the 7 of their papers we have counts for
7 papers
LookThere! Sparse Vision by Reinforced Selection
Sreehari Rammohan, Yousef Yassin, Anthony Fuller +3
Vision transformers typically treat every image token as equally important, yet for most tasks in computer vision only a fraction are needed. Adaptive computation methods accelerat…
Robot Critics that Sweat the Small Stuff
Sruthi Sudhakar, Junbang Liang, Sreehari Rammohan +3
Large vision-language models contain several priors about the world and object interactions, making them useful critics during inference to steer robot policies towards success. Ho…
: Smaller Self-Supervised ViTs Localize Better than Larger Ones
Sreehari Rammohan, Huy Ha, Carl Vondrick
Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we find that the attention map…
Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning
Andrew Levy, Sreehari Rammohan, Alessandro Allievi +2
General purpose agents will require large repertoires of skills. Empowerment -- the maximum mutual information between skills and states -- provides a pathway for learning large co…
Hierarchical Reinforcement Learning of Locomotion Policies in Response to Approaching Objects: A Preliminary Study
Shangqun Yu, Sreehari Rammohan, Kaiyu Zheng +1
Animals such as rabbits and birds can instantly generate locomotion behavior in reaction to a dynamic, approaching object, such as a person or a rock, despite having possibly never…
Does DQN really learn? Exploring adversarial training schemes in Pong
Bowen He, Sreehari Rammohan, Jessica Forde +1
In this work, we study two self-play training schemes, Chainer and Pool, and show they lead to improved agent performance in Atari Pong compared to a standard DQN agent -- trained…
Value-Based Reinforcement Learning for Continuous Control Robotic Manipulation in Multi-Task Sparse Reward Settings
Sreehari Rammohan, Shangqun Yu, Bowen He +4
Learning continuous control in high-dimensional sparse reward settings, such as robotic manipulation, is a challenging problem due to the number of samples often required to obtain…