Search Results for author: Daiki Kimura

Found 17 papers, 4 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

DiffG-RL: Leveraging Difference between State and Common Sense

1 code implementation29 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.

Common Sense Reasoning text-based games

Commonsense Knowledge from Scene Graphs for Textual Environments

no code implementations19 Oct 2022 Tsunehiko Tanaka, Daiki Kimura, Michiaki Tatsubori

They are usually imperfect information games, and their interactions are only in the textual modality.

Common Sense Reasoning text-based games

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

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)

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

Spatially-weighted Anomaly Detection with Regression Model

no code implementations23 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.

Anomaly Detection regression

Spatially-weighted Anomaly Detection

no code implementations5 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.

Anomaly Detection

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

DAQN: Deep Auto-encoder and Q-Network

no code implementations2 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.

reinforcement-learning Reinforcement Learning (RL)

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

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