26 citations · 49 across the 15 of their papers we have counts for
15 papers
Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games
Somjit Nath, Abdelhak Lemkhenter, Pallavi Choudhury +4
Imitation learning is an appealing way to scale game-playing agents to complex 3D environments by training policies to map visual observations to actions from human demonstrations.…
Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion
Somjit Nath, Jackson J Cone, Derek Nowrouzezahrai +1
Neuroscientific research has revealed that the brain encodes complex behaviors by leveraging structured, low-dimensional manifolds and dynamically fusing multiple sources of inform…
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
Parsa Esmati, Somjit Nath, Katja Hofmann +3
Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether the…
When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter +10
Behavior cloning (BC) is a practical offline imitation learning method, but it often fails when expert demonstrations are limited. Recent works have introduced a class of architect…
Behaviour Discovery and Attribution for Explainable Reinforcement Learning
Rishav Rishav, Somjit Nath, Vincent Michalski +1
Building trust in reinforcement learning (RL) agents requires understanding why they make certain decisions, especially in high-stakes applications like robotics, healthcare, and f…
Unsupervised Event Outlier Detection in Continuous Time
Somjit Nath, Yik Chau Lui, Siqi Liu
Event sequence data record the occurrences of events in continuous time. Event sequence forecasting based on temporal point processes (TPPs) has been extensively studied, but outli…
Spectral Temporal Contrastive Learning
Sacha Morin, Somjit Nath, Samira Ebrahimi Kahou +1
Learning useful data representations without requiring labels is a cornerstone of modern deep learning. Self-supervised learning methods, particularly contrastive learning (CL), ha…
Discovering Object-Centric Generalized Value Functions From Pixels
Somjit Nath, Gopeshh Raaj Subbaraj, Khimya Khetarpal +1
Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using hand-crafted auxiliary tasks and pseudo re…
Locally Constrained Representations in Reinforcement Learning
Somjit Nath, Rushiv Arora, Samira Ebrahimi Kahou
The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representation…
Prioritizing Samples in Reinforcement Learning with Reducible Loss
Shivakanth Sujit, Somjit Nath, Pedro H. M. Braga +1
Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the sa…
A Learning Based Framework for Handling Uncertain Lead Times in Multi-Product Inventory Management
Hardik Meisheri, Somjit Nath, Mayank Baranwal +1
Most existing literature on supply chain and inventory management consider stochastic demand processes with zero or constant lead times. While it is true that in certain niche scen…
Follow your Nose: Using General Value Functions for Directed Exploration in Reinforcement Learning
Durgesh Kalwar, Omkar Shelke, Somjit Nath +2
Improving sample efficiency is a key challenge in reinforcement learning, especially in environments with large state spaces and sparse rewards. In literature, this is resolved eit…
Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays
Somjit Nath, Mayank Baranwal, Harshad Khadilkar
Several real-world scenarios, such as remote control and sensing, are comprised of action and observation delays. The presence of delays degrades the performance of reinforcement l…
Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains
Nazneen N Sultana, Hardik Meisheri, Vinita Baniwal +3
This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains. The problem description and solution are both adapted fr…
SIBRE: Self Improvement Based REwards for Adaptive Feedback in Reinforcement Learning
Somjit Nath, Richa Verma, Abhik Ray +1
We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is…