no code implementations • 8 Oct 2023 • Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli, Huazheng Wang, Qingyun Wu, Haoyu Zhao
Contrary to prior understanding of multi-armed bandits, our work reveals a surprising fact that the attackability of a specific CMAB instance also depends on whether the bandit instance is known or unknown to the adversary.
no code implementations • 27 Jun 2022 • Alexander Matt Turner, Prasad Tadepalli
We show that a range of qualitatively dissimilar decision-making procedures incentivize agents to seek power.
no code implementations • 23 Jun 2022 • Alexander Matt Turner, Aseem Saxena, Prasad Tadepalli
AI objectives are often hard to specify properly.
no code implementations • 16 Jun 2022 • Siwen Yan, Sriraam Natarajan, Saket Joshi, Roni Khardon, Prasad Tadepalli
Ensemble models (bagging and gradient-boosting) of relational decision trees have proved to be one of the most effective learning methods in the area of probabilistic logic models (PLMs).
no code implementations • 15 Oct 2021 • Harsha Kokel, Arjun Manoharan, Sriraam Natarajan, Balaraman Ravindran, Prasad Tadepalli
State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments.
no code implementations • 13 Sep 2021 • Li Fuxin, Zhongang Qi, Saeed Khorram, Vivswan Shitole, Prasad Tadepalli, Minsuk Kahng, Alan Fern
This paper summarizes our endeavors in the past few years in terms of explaining image classifiers, with the aim of including negative results and insights we have gained.
1 code implementation • EMNLP 2021 • Yilin Yang, Akiko Eriguchi, Alexandre Muzio, Prasad Tadepalli, Stefan Lee, Hany Hassan
At the gradient level, we leverage a small amount of direct data (in thousands of sentence pairs) to regularize model gradients.
1 code implementation • NeurIPS 2021 • Vivswan Shitole, Li Fuxin, Minsuk Kahng, Prasad Tadepalli, Alan Fern
Attention maps are a popular way of explaining the decisions of convolutional networks for image classification.
2 code implementations • ICLR 2021 • Aayam Shrestha, Stefan Lee, Prasad Tadepalli, Alan Fern
We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Yilin Yang, Longyue Wang, Shuming Shi, Prasad Tadepalli, Stefan Lee, Zhaopeng Tu
There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains largely unexamined despite its critical role.
2 code implementations • NeurIPS 2020 • Alexander Matt Turner, Neale Ratzlaff, Prasad Tadepalli
By preserving optimal value for a single randomly generated reward function, AUP incurs modest overhead while leading the agent to complete the specified task and avoid many side effects.
no code implementations • ACL 2020 • Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini, Prasad Tadepalli
Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences.
1 code implementation • NeurIPS 2021 • Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, Prasad Tadepalli
Some researchers speculate that intelligent reinforcement learning (RL) agents would be incentivized to seek resources and power in pursuit of their objectives.
no code implementations • 1 Oct 2019 • Murugeswari Issakkimuthu, Alan Fern, Prasad Tadepalli
There are notable examples of online search improving over hand-coded or learned policies (e. g. AlphaZero) for sequential decision making.
no code implementations • 14 Aug 2019 • Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini, Rasha Obeidat, Prasad Tadepalli
We present a new local entity disambiguation system.
no code implementations • NAACL 2019 • Rasha Obeidat, Xiaoli Fern, Hamed Shahbazi, Prasad Tadepalli
Fine-grained Entity typing (FGET) is the task of assigning a fine-grained type from a hierarchy to entity mentions in the text.
3 code implementations • 26 Feb 2019 • Alexander Matt Turner, Dylan Hadfield-Menell, Prasad Tadepalli
Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified reward function can irreversibly change the state of its environment.
no code implementations • NAACL 2019 • Reza Ghaeini, Xiaoli Z. Fern, Hamed Shahbazi, Prasad Tadepalli
Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances.
no code implementations • 18 Dec 2018 • Mandana Hamidi-Haines, Zhongang Qi, Alan Fern, Fuxin Li, Prasad Tadepalli
For this purpose, we developed a user interface for "interactive naming," which allows a human annotator to manually cluster significant activation maps in a test set into meaningful groups called "visual concepts".
no code implementations • 11 Sep 2018 • J. Walker Orr, Prasad Tadepalli, Janardhan Rao Doppa, Xiaoli Fern, Thomas G. Dietterich
Scripts have been proposed to model the stereotypical event sequences found in narratives.
no code implementations • 9 Sep 2018 • Reza Ghaeini, Xiaoli Z. Fern, Prasad Tadepalli
We also study the behavior of the proposed model to provide explanations for the model's decisions.
no code implementations • EMNLP 2018 • J. Walker Orr, Prasad Tadepalli, Xiaoli Fern
Detecting events and classifying them into predefined types is an important step in knowledge extraction from natural language texts.
no code implementations • EMNLP 2018 • Reza Ghaeini, Xiaoli Z. Fern, Prasad Tadepalli
Deep learning models have achieved remarkable success in natural language inference (NLI) tasks.
no code implementations • COLING 2018 • Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini, Chao Ma, Rasha Obeidat, Prasad Tadepalli
In this paper, we present a novel model for entity disambiguation that combines both local contextual information and global evidences through Limited Discrepancy Search (LDS).
no code implementations • COLING 2018 • Reza Ghaeini, Xiaoli Z. Fern, Hamed Shahbazi, Prasad Tadepalli
We present a novel deep learning architecture to address the cloze-style question answering task.
no code implementations • ACL 2016 • Reza Ghaeini, Xiaoli Z. Fern, Liang Huang, Prasad Tadepalli
Traditional event detection methods heavily rely on manually engineered rich features.
no code implementations • 18 Apr 2014 • Robby Goetschalckx, Alan Fern, Prasad Tadepalli
Coactive learning is an online problem solving setting where the solutions provided by a solver are interactively improved by a domain expert, which in turn drives learning.
no code implementations • NeurIPS 2013 • Aswin Raghavan, Roni Khardon, Alan Fern, Prasad Tadepalli
We address the scalability of symbolic planning under uncertainty with factored states and actions.
no code implementations • NeurIPS 2012 • Aaron Wilson, Alan Fern, Prasad Tadepalli
We consider the problem of learning control policies via trajectory preference queries to an expert.
no code implementations • NeurIPS 2011 • Neville Mehta, Prasad Tadepalli, Alan Fern
This paper introduces two new frameworks for learning action models for planning.
no code implementations • NeurIPS 2011 • Mohammad S. Sorower, Janardhan R. Doppa, Walker Orr, Prasad Tadepalli, Thomas G. Dietterich, Xiaoli Z. Fern
However, unlike standard approaches to missing data, in this setting we know that facts are more likely to be missing from the text in cases where the reader can infer them from the facts that are mentioned combined with the domain knowledge.
no code implementations • NeurIPS 2010 • Alan Fern, Prasad Tadepalli
A variation of this policy is shown to achieve worst-case regret that is logarithmic in the number of goals for any goal distribution.