no code implementations • 7 Aug 2023 • Nirbhay Modhe, Qiaozi Gao, Ashwin Kalyan, Dhruv Batra, Govind Thattai, Gaurav Sukhatme
Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions.
1 code implementation • 26 Jun 2021 • Nirbhay Modhe, Harish Kamath, Dhruv Batra, Ashwin Kalyan
This work shows that value-aware model learning, known for its numerous theoretical benefits, is also practically viable for solving challenging continuous control tasks in prevalent model-based reinforcement learning algorithms.
no code implementations • ICML Workshop LifelongML 2020 • Nirbhay Modhe, Harish K Kamath, Dhruv Batra, Ashwin Kalyan
Despite the breakthroughs achieved by Reinforcement Learning (RL) in recent years, RL agents often fail to perform well in unseen environments.
no code implementations • 25 Sep 2019 • Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
We learn to identify decision states, namely the parsimonious set of states where decisions meaningfully affect the future states an agent can reach in an environment.
no code implementations • 24 Jul 2019 • Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
We propose a novel framework to identify sub-goals useful for exploration in sequential decision making tasks under partial observability.
no code implementations • ICML 2017 • Vikas Jain, Nirbhay Modhe, Piyush Rai
We present a scalable, generative framework for multi-label learning with missing labels.