Ishan Durugkar Research Scientist at Sony AI Zola 2025-10-22T00:00:00+00:00 https://idurugkar.github.io/atom.xml Semantic World Models 2025-10-22T00:00:00+00:00 2025-10-22T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/semantic-world-models/ Sequence Modeling for N-Agent Ad Hoc Teamwork 2025-06-04T00:00:00+00:00 2025-06-04T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/sequence-modeling-naht/ N-Agent Ad Hoc Teamwork 2024-12-10T00:00:00+00:00 2024-12-10T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/n-agent-adhoc-teamwork/ f-Policy Gradients: A General Framework for Goal-Conditioned RL using f-Divergences 2023-12-10T00:00:00+00:00 2023-12-10T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/f-policy-gradients/ DM²: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching 2023-02-14T00:00:00+00:00 2023-02-14T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/dm2/ ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning 2022-12-03T00:00:00+00:00 2022-12-03T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/abc-adversarial-cloning/ Towards a Real-Time, Low-Resource, End-to-End Object Detection Pipeline for Robot Soccer 2022-07-01T00:00:00+00:00 2022-07-01T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/robot-soccer-detection/ Wasserstein Distance Maximizing Intrinsic Control 2021-10-28T00:00:00+00:00 2021-10-28T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/wic/ Adversarial Intrinsic Motivation for Reinforcement Learning 2021-10-18T00:00:00+00:00 2021-10-18T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/aim/ On Sampling Error in Batch Action-Value Prediction Algorithms 2020-12-12T00:00:00+00:00 2020-12-12T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/sampling-error-batch-td/ An Imitation from Observation Approach to Sim-to-Real Transfer 2020-11-16T00:00:00+00:00 2020-11-16T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/ifo-transfer/ Balancing Individual Preferences and Shared Objectives in Multiagent Reinforcement Learning 2020-07-24T00:00:00+00:00 2020-07-24T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/multiagent-prefs/ Reducing Sampling Error in Batch Temporal Difference Learning 2020-07-13T00:00:00+00:00 2020-07-13T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/psec-td/ Multi-Preference Actor Critic 2019-07-11T00:00:00+00:00 2019-07-11T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/multi-preference-actor-critic/ Go for a Walk and Arrive at the Answer: Reasoning over Paths in Knowledge Bases using Reinforcement Learning 2018-05-03T00:00:00+00:00 2018-05-03T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/minerva/ TD Learning with Constrained Gradients 2017-12-07T00:00:00+00:00 2017-12-07T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/constrained-td/ Unmixing in the Presence of Nuisances with Deep Generative Models 2017-07-23T00:00:00+00:00 2017-07-23T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/unmixing-generative/ Generative Multi-Adversarial Networks 2017-04-24T00:00:00+00:00 2017-04-24T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/gman/ Predictive Off-Policy Policy Evaluation for Nonstationary Decision Problems, with Applications to Digital Marketing 2017-02-08T00:00:00+00:00 2017-02-08T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/nonstationary-ope/ Inverting Variational Autoencoders for Improved Generative Accuracy 2016-08-21T00:00:00+00:00 2016-08-21T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/inverted-vae/ Deep Reinforcement Learning with Macro-Actions 2016-06-15T00:00:00+00:00 2016-06-15T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/macro-actions/ Cohort Intelligence: A Self Supervised Learning Behavior 2013-10-13T00:00:00+00:00 2013-10-13T00:00:00+00:00 Unknown https://idurugkar.github.io/publications/cohort-intelligence/