Search Publications

@inproceedings{Kritika22,
title = {How Private Is Your RL Policy? An Inverse RL Based Analysis Framework},
author = {Kritika Prakash and Fiza Hussain and Praveen Paruchuri and Sujit Gujar},
year = {2022},
date = {2022-02-22},
booktitle = {36th AAAI Conference on Artificial Intelligence },
publisher = {AAAI},
keywords = {differential privacy, inverse reinforcement learning, Reinforcement Learning},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}

@inproceedings{gear2020predictrv,
title = {PredictRV: A Prediction Based Strategy for Negotiations with Dynamically Changing Reservation Value},
author = {Aditya Srinivas Gear and Kritika Prakash and Nonidh Singh and Praveen Paruchuri},
year = {2020},
date = {2020-01-01},
booktitle = {International Conference on Group Decision and Negotiation},
pages = {135--148},
organization = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{10.1007/978-3-030-48641-9_10,
title = {PredictRV: A Prediction Based Strategy for Negotiations with Dynamically Changing Reservation Value},
author = {Aditya Srinivas Gear and Kritika Prakash and Nonidh Singh and Praveen Paruchuri},
editor = {Danielle Costa Morais and Liping Fang and Masahide Horita},
isbn = {978-3-030-48641-9},
year = {2020},
date = {2020-01-01},
booktitle = {Group Decision and Negotiation: A Multidisciplinary Perspective},
pages = {135--148},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Negotiation is an important component of the interaction process among humans. With increasing automation, autonomous agents are expected to take over a lot of this interaction process. Much of automated negotiation literature focuses on agents having a static and known reservation value. In situations involving dynamic environments e.g., an agent negotiating on behalf of a human regarding a meeting, agents can have a reservation value (RV) that is a function of time. This leads to a different set of challenges that may need additional reasoning about the concession behavior. In this paper, we build upon Negotiation algorithms such as ONAC (Optimal Non-Adaptive Concession) and Time-Dependent Techniques such as Boulware which work on settings where the reservation value of the agent is fixed and known. Although these algorithms can encode dynamic RV, their concession behavior and hence the properties they were expected to display would be different from when the RV is static, even though the underlying negotiation algorithm remains the same. We, therefore, propose to use one of Counter, Bayesian Learning with Regression Analysis or LSTM model on top of each algorithm to develop the PredictRV strategy and show that PredictRV indeed performs better on two different metrics tested on two different domains on a variety of parameter settings.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{ghosh2019vidyutvanika,
title = {Vidyutvanika: An autonomous broker agent for smart grid environment},
author = {Susobhan Ghosh and Kritika Prakash and Sanjay Chandlekar and Easwar Subramanian and Sanjay P Bhat and Sujit Gujar and Praveen Paruchuri},
year = {2019},
date = {2019-01-01},
booktitle = {PASS},
volume = {7},
publisher = {Policy, Awareness, Sustainability and Systems (PASS) Workshop},
keywords = {Reinforcement Learning, smart grids},
pubstate = {published},
tppubtype = {inproceedings}
}