Takip et
Somjit Nath
Somjit Nath
McGill University, Mila
mail.mcgill.ca üzerinde doğrulanmış e-posta adresine sahip - Ana Sayfa
Başlık
Alıntı yapanlar
Alıntı yapanlar
Yıl
Arduino based door unlocking system with real time control
S Nath, P Banerjee, RN Biswas, SK Mitra, MK Naskar
2016 2nd International conference on contemporary computing and informatics …, 2016
642016
Two-timescale networks for nonlinear value function approximation
W Chung, S Nath, A Joseph, M White
International Conference on Learning Representations (ICLR) 2019, 2019
572019
Reinforcement learning for multi-product multi-node inventory management in supply chains
NN Sultana, H Meisheri, V Baniwal, S Nath, B Ravindran, H Khadilkar
arXiv preprint arXiv:2006.04037, 2020
422020
Scalable multi-product inventory control with lead time constraints using reinforcement learning
H Meisheri, NN Sultana, M Baranwal, V Baniwal, S Nath, S Verma, ...
Neural Computing and Applications 34 (3), 1735-1757, 2022
382022
Revisiting state augmentation methods for reinforcement learning with stochastic delays
S Nath, M Baranwal, H Khadilkar
Proceedings of the 30th ACM international conference on information …, 2021
352021
Prioritizing samples in reinforcement learning with reducible loss
S Sujit, S Nath, PHM Braga, SE Kahou
Conference on Neural Information Processing Systems (NeurIPS), 2022
212022
Training recurrent neural networks online by learning explicit state variables
S Nath, V Liu, A Chan, X Li, A White, M White
International Conference on Learning Representations (ICLR) 2020, 2019
62019
Smartphone camera‐based analysis of ELISA using artificial neural network
S Nath, S Sarcar, B Chatterjee, R Chourashi, NS Chatterjee
IET Computer Vision 12 (6), 826-833, 2018
62018
Reinforcement learning for multi-product multi-node inventory management in supply chains. arXiv 2020
NN Sultana, H Meisheri, V Baniwal, S Nath, B Ravindran, H Khadilkar
arXiv preprint arXiv:2006.04037, 2020
52020
Discovering Object-Centric Generalized Value Functions From Pixels
S Nath, GR Subbaraj, K Khetarpal, SE Kahou
International Conference on Machine Learning (ICML) 2023, 2023
32023
CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning
N Gupta, S Nath, SE Kahou
arXiv preprint arXiv:2306.11128, 2023
22023
A Learning Based Framework for Handling Uncertain Lead Times in Multi-Product Inventory Management
H Meisheri, S Nath, M Baranwal, H Khadilkar
arXiv preprint arXiv:2203.00885, 2022
22022
Fixed Point Propagation: A New Way To Train Recurrent Neural Networks Using Auxiliary Variables
S Nath
12019
Behaviour Discovery and Attribution for Explainable Reinforcement Learning
R Rishav, S Nath, V Michalski, SE Kahou
arXiv preprint arXiv:2503.14973, 2025
2025
Unsupervised Event Outlier Detection in Continuous Time
S Nath, YC Lui, S Liu
arXiv preprint arXiv:2411.16427, 2024
2024
Task-Oriented Slot-Based Cumulant Discovery in General Value Functions
V Michalski, S Nath, D Nowrouzezahrai, D Precup, SE Kahou
Workshop on Reinforcement Learning Beyond Rewards@ Reinforcement Learning …, 2024
2024
Spectral Temporal Contrastive Learning
S Morin, S Nath, SE Kahou, G Wolf
NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice, 2023
2023
Locally Constrained Representations in Reinforcement Learning
S Nath, R Arora, SE Kahou
NeurIPS 2022: Deep RL Workshop, 2022
2022
Follow your Nose: Using General Value Functions for Directed Exploration in Reinforcement Learning
S Nath, O Shelke, D Kalwar, H Meisheri, H Khadilkar
International Conference on Autonomous Agents and Multiagent Systems (AAMAS …, 2022
2022
SIBRE: Self Improvement Based REwards for Adaptive Feedback in Reinforcement Learning
S Nath, R Verma, A Ray, H Khadilkar
The International Conference on Autonomous Agents and Multiagent Systems, 2020
2020
Sistem, işlemi şu anda gerçekleştiremiyor. Daha sonra yeniden deneyin.
Makaleler 1–20
OSZAR »