Search Results for author: Subhajit Chaudhury

Found 35 papers, 11 papers with code

Neuro-Symbolic Approaches for Text-Based Policy Learning

1 code implementation EMNLP 2021 Subhajit Chaudhury, Prithviraj Sen, Masaki Ono, Daiki Kimura, Michiaki Tatsubori, Asim Munawar

We outline a method for end-to-end differentiable symbolic rule learning and show that such symbolic policies outperform previous state-of-the-art methods in text-based RL for the coin collector environment from 5-10x fewer training games.

Reinforcement Learning (RL) text-based games

On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning

no code implementations15 Apr 2024 Mauricio Gruppi, Soham Dan, Keerthiram Murugesan, Subhajit Chaudhury

Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL).

reinforcement-learning

Larimar: Large Language Models with Episodic Memory Control

no code implementations18 Mar 2024 Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aurélie Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jiří, Navrátil, Soham Dan, Pin-Yu Chen

Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today.

API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs

1 code implementation23 Feb 2024 Kinjal Basu, Ibrahim Abdelaziz, Subhajit Chaudhury, Soham Dan, Maxwell Crouse, Asim Munawar, Sadhana Kumaravel, Vinod Muthusamy, Pavan Kapanipathi, Luis A. Lastras

There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks.

Benchmarking slot-filling +2

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $ε$-Greedy Exploration

no code implementations24 Oct 2023 Shuai Zhang, Hongkang Li, Meng Wang, Miao Liu, Pin-Yu Chen, Songtao Lu, Sijia Liu, Keerthiram Murugesan, Subhajit Chaudhury

This paper provides the first theoretical convergence and sample complexity analysis of the practical setting of DQNs with $\epsilon$-greedy policy.

Q-Learning

Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning

1 code implementation5 Jul 2023 Subhajit Chaudhury, Sarathkrishna Swaminathan, Daiki Kimura, Prithviraj Sen, Keerthiram Murugesan, Rosario Uceda-Sosa, Michiaki Tatsubori, Achille Fokoue, Pavan Kapanipathi, Asim Munawar, Alexander Gray

Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games.

reinforcement-learning Representation Learning

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach

1 code implementation23 Oct 2022 Heshan Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen

Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them.

Fairness Inductive Bias +1

LOA: Logical Optimal Actions for Text-based Interaction Games

1 code implementation ACL 2021 Daiki Kimura, Subhajit Chaudhury, Masaki Ono, Michiaki Tatsubori, Don Joven Agravante, Asim Munawar, Akifumi Wachi, Ryosuke Kohita, Alexander Gray

We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games.

reinforcement-learning Reinforcement Learning (RL) +1

Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents

no code implementations9 Jun 2021 Keerthiram Murugesan, Subhajit Chaudhury, Kartik Talamadupula

This improves the agent's overall understanding of the game 'scene' and objects' relationships to the world around them, and the variety of visual representations on offer allow the agent to generate a better generalization of a relationship.

reinforcement-learning Reinforcement Learning (RL) +2

Reinforcement Learning with External Knowledge by using Logical Neural Networks

no code implementations3 Mar 2021 Daiki Kimura, Subhajit Chaudhury, Akifumi Wachi, Ryosuke Kohita, Asim Munawar, Michiaki Tatsubori, Alexander Gray

Specifically, we propose an integrated method that enables model-free reinforcement learning from external knowledge sources in an LNNs-based logical constrained framework such as action shielding and guide.

reinforcement-learning Reinforcement Learning (RL)

Image inpainting using frequency domain priors

1 code implementation3 Dec 2020 Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki, Tatsuaki Hashimoto

To alleviate these problems, we investigate if it is possible to obtain better performance by training the networks using frequency domain information (Discrete Fourier Transform) along with the spatial domain information.

Image Inpainting

VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning

no code implementations26 Oct 2020 Thomas Carta, Subhajit Chaudhury, Kartik Talamadupula, Michiaki Tatsubori

The goal is to force an RL agent to use both text and visual features to predict natural language action commands for solving the final task of cooking a meal.

Atari Games reinforcement-learning +2

Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games

1 code implementation EMNLP 2020 Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori, Asim Munawar, Ryuki Tachibana

Our bootstrapped agent shows improved generalization in solving unseen TextWorld games, using 10x-20x fewer training games compared to previous state-of-the-art methods despite requiring less number of training episodes.

Q-Learning Reinforcement Learning (RL) +1

Investigating Generalization in Neural Networks under Optimally Evolved Training Perturbations

1 code implementation14 Mar 2020 Subhajit Chaudhury, Toshihiko Yamasaki

In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting.

Domain Adaptation

Assessing Robustness of Deep learning Methods in Dermatological Workflow

no code implementations15 Jan 2020 Sourav Mishra, Subhajit Chaudhury, Hideaki Imaizumi, Toshihiko Yamasaki

This paper aims to evaluate the suitability of current deep learning methods for clinical workflow especially by focusing on dermatology.

Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning

no code implementations2 Oct 2018 Subhajit Chaudhury, Daiki Kimura, Asim Munawar, Ryuki Tachibana

Experimental results show that the proposed adversarial learning method from raw videos produces a similar performance to state-of-the-art imitation learning techniques while frequently outperforming existing hand-crafted video imitation methods.

Imitation Learning

Constrained Exploration and Recovery from Experience Shaping

1 code implementation21 Sep 2018 Tu-Hoa Pham, Giovanni De Magistris, Don Joven Agravante, Subhajit Chaudhury, Asim Munawar, Ryuki Tachibana

We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding undesirable actions or states, associated to lower rewards, or penalties.

reinforcement-learning Reinforcement Learning (RL)

Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection

no code implementations4 Jul 2018 Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data.

Position Transfer Learning

Internal Model from Observations for Reward Shaping

no code implementations2 Jun 2018 Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana, Sakyasingha Dasgupta

During reinforcement learning, the agent predicts the reward as a function of the difference between the actual state and the state predicted by the internal model.

reinforcement-learning Reinforcement Learning (RL)

Reward Estimation via State Prediction

no code implementations ICLR 2018 Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana, Sakyasingha Dasgupta

We present a novel reward estimation method that is based on a finite sample of optimal state trajectories from expert demon- strations and can be used for guiding an agent to mimic the expert behavior.

reinforcement-learning Reinforcement Learning (RL)

Model-based imitation learning from state trajectories

no code implementations ICLR 2018 Subhajit Chaudhury, Daiki Kimura, Tadanobu Inoue, Ryuki Tachibana

We present a model-based imitation learning method that can learn environment-specific optimal actions only from expert state trajectories.

Imitation Learning reinforcement-learning +1

Conditional generation of multi-modal data using constrained embedding space mapping

no code implementations4 Jul 2017 Subhajit Chaudhury, Sakyasingha Dasgupta, Asim Munawar, Md. A. Salam Khan, Ryuki Tachibana

We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships between them.

Can fully convolutional networks perform well for general image restoration problems?

no code implementations14 Nov 2016 Subhajit Chaudhury, Hiya Roy

We propose a fully convolutional model, that learns a direct end-to-end mapping between the corrupted images as input and the desired clean images as output.

Image Denoising Image Inpainting +3

Cannot find the paper you are looking for? You can Submit a new open access paper.