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.
1 code implementation • 29 Nov 2022 • Tsunehiko Tanaka, Daiki Kimura, Michiaki Tatsubori
We propose a novel agent, DiffG-RL, which constructs a Difference Graph that organizes the environment states and common sense by means of interactive objects with a dedicated graph encoder.
no code implementations • 19 Oct 2022 • Tsunehiko Tanaka, Daiki Kimura, Michiaki Tatsubori
They are usually imperfect information games, and their interactions are only in the textual modality.
no code implementations • EMNLP 2021 • Daiki Kimura, Masaki Ono, Subhajit Chaudhury, Ryosuke Kohita, Akifumi Wachi, Don Joven Agravante, Michiaki Tatsubori, Asim Munawar, Alexander Gray
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided.
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.
no code implementations • 3 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.
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.
no code implementations • 19 Feb 2020 • Subhajit Chaudhury, Daiki Kimura, Phongtharin Vinayavekhin, Asim Munawar, Ryuki Tachibana, Koji Ito, Yuki Inaba, Minoru Matsumoto, Shuji Kidokoro, Hiroki Ozaki
In this paper, we study the case of event detection in sports videos for unstructured environments with arbitrary camera angles.
no code implementations • 23 Mar 2019 • Daiki Kimura, Minori Narita, Asim Munawar, Ryuki Tachibana
Visual anomaly detection is common in several applications including medical screening and production quality check.
no code implementations • 5 Oct 2018 • Minori Narita, Daiki Kimura, Ryuki Tachibana
Many types of anomaly detection methods have been proposed recently, and applied to a wide variety of fields including medical screening and production quality checking.
no code implementations • 2 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.
no code implementations • 22 Jun 2018 • Phongtharin Vinayavekhin, Subhajit Chaudhury, Asim Munawar, Don Joven Agravante, Giovanni De Magistris, Daiki Kimura, Ryuki Tachibana
This paper is a contribution towards interpretability of the deep learning models in different applications of time-series.
no code implementations • 2 Jun 2018 • Daiki Kimura
When it is extended a real-task in the real environment with an actual robot, the method will be required more training images due to complexities or noises of the input images, and executing a lot of actions on the real robot also becomes a serious problem.
no code implementations • 2 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.
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.
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.