Tanmay Gangwani

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 26

Top Topics

Imitation Learning

Transition Model

Top Venues

Publications

Yinuo Ren, Tesi Xiao, Tanmay Gangwani, Anshuka Rangi, Holakou Rahmanian, Lexing Ying, Subhajit Sanyal
Multi-objective Optimization via Wasserstein-Fisher-Rao Gradient Flow. AISTATS (2024)
Yinuo Ren, Tesi Xiao, Tanmay Gangwani, Anshuka Rangi, Holakou Rahmanian, Lexing Ying, Subhajit Sanyal
Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow. CoRR (2023)
Tesi Xiao, Branislav Kveton, Sumeet Katariya, Tanmay Gangwani, Anshuka Rangi
Towards Sequential Counterfactual Learning to Rank. SIGIR-AP (2023)
Sanath Kumar Krishnamurthy, Tanmay Gangwani, Sumeet Katariya, Branislav Kveton, Anshuka Rangi
Selective Uncertainty Propagation in Offline RL. CoRR (2023)
Tanmay Gangwani, Yuan Zhou, Jian Peng
Imitation Learning from Observations under Transition Model Disparity. ICLR (2022)
Michael Wan, Jian Peng, Tanmay Gangwani
Hindsight Foresight Relabeling for Meta-Reinforcement Learning. ICLR (2022)
Tanmay Gangwani, Yuan Zhou, Jian Peng
Imitation Learning from Observations under Transition Model Disparity. CoRR (2022)
Michael Wan, Jian Peng, Tanmay Gangwani
Hindsight Foresight Relabeling for Meta-Reinforcement Learning. CoRR (2021)
Tanmay Gangwani, Yuan Zhou, Jian Peng
Learning Guidance Rewards with Trajectory-space Smoothing. NeurIPS (2020)
Tanmay Gangwani, Jian Peng, Yuan Zhou
Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity. CoRL (2020)
Tanmay Gangwani, Jian Peng
State-only Imitation with Transition Dynamics Mismatch. CoRR (2020)
Azin Heidarshenas, Tanmay Gangwani, Serif Yesil, Adam Morrison, Josep Torrellas
Snug: architectural support for relaxed concurrent priority queueing in chip multiprocessors. ICS (2020)
Michael Wan, Tanmay Gangwani, Jian Peng
Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch. CoRR (2020)
Tanmay Gangwani, Yuan Zhou, Jian Peng
Learning Guidance Rewards with Trajectory-space Smoothing. CoRR (2020)
Tanmay Gangwani, Jian Peng
State-only Imitation with Transition Dynamics Mismatch. ICLR (2020)
Michael Wan, Tanmay Gangwani, Jian Peng
Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch. UAI (2020)
Tanmay Gangwani, Jian Peng, Yuan Zhou
Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity. CoRR (2020)
Tanmay Gangwani, Joel Lehman, Qiang Liu, Jian Peng
Learning Belief Representations for Imitation Learning in POMDPs. CoRR (2019)
Tanmay Gangwani, Joel Lehman, Qiang Liu, Jian Peng
Learning Belief Representations for Imitation Learning in POMDPs. UAI (2019)
Sandeep Dasgupta, Tanmay Gangwani
Partial Redundancy Elimination using Lazy Code Motion. CoRR (2019)
Tanmay Gangwani, Qiang Liu, Jian Peng
Learning Self-Imitating Diverse Policies. ICLR (Poster) (2019)
Tanmay Gangwani, Jian Peng
Policy Optimization by Genetic Distillation. ICLR (Poster) (2018)
Tanmay Gangwani, Qiang Liu, Jian Peng
Learning Self-Imitating Diverse Policies. CoRR (2018)
Yunhui Long, Tanmay Gangwani, Haris Mughees, Carl A. Gunter
Distributed and Secure ML with Self-tallying Multi-party Aggregation. CoRR (2018)
Tanmay Gangwani, Jian Peng
Genetic Policy Optimization. CoRR (2017)
Tanmay Gangwani, Adam Morrison, Josep Torrellas
CASPAR: Breaking Serialization in Lock-Free Multicore Synchronization. ASPLOS (2016)