19 citations · 44 across the 12 of their papers we have counts for
12 papers
Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences
Takuya Hiraoka, Guanquan Wang, Takashi Onishi +1
In reinforcement learning (RL) with experience replay, experiences stored in a replay buffer influence the RL agent's performance. Information about how these experiences influence…
Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout
Takuya Hiraoka, Takashi Onishi, Yoshimasa Tsuruoka
In reinforcement learning (RL) with experience replay, experiences stored in a replay buffer influence the RL agent's performance. Information about the influence is valuable for v…
Soft Sensors and Process Control using AI and Dynamic Simulation
Shumpei Kubosawa, Takashi Onishi, Yoshimasa Tsuruoka
During the operation of a chemical plant, product quality must be consistently maintained, and the production of off-specification products should be minimized. Accordingly, proces…
Railway Operation Rescheduling System via Dynamic Simulation and Reinforcement Learning
Shumpei Kubosawa, Takashi Onishi, Makoto Sakahara +1
The number of railway service disruptions has been increasing owing to intensification of natural disasters. In addition, abrupt changes in social situations such as the COVID-19 p…
Dropout Q-Functions for Doubly Efficient Reinforcement Learning
Takuya Hiraoka, Takahisa Imagawa, Taisei Hashimoto +2
Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks.…
Meta-Model-Based Meta-Policy Optimization
Takuya Hiraoka, Takahisa Imagawa, Voot Tangkaratt +3
Model-based meta-reinforcement learning (RL) methods have recently been shown to be a promising approach to improving the sample efficiency of RL in multi-task settings. However, t…
Learning Robust Options by Conditional Value at Risk Optimization
Takuya Hiraoka, Takahisa Imagawa, Tatsuya Mori +2
Options are generally learned by using an inaccurate environment model (or simulator), which contains uncertain model parameters. While there are several methods to learn options t…
Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning
Shumpei Kubosawa, Takashi Onishi, Yoshimasa Tsuruoka
Chemical plants are complex and dynamical systems consisting of many components for manipulation and sensing, whose state transitions depend on various factors such as time, distur…
Refining Manually-Designed Symbol Grounding and High-Level Planning by Policy Gradients
Takuya Hiraoka, Takashi Onishi, Takahisa Imagawa +1
Hierarchical planners that produce interpretable and appropriate plans are desired, especially in its application to supporting human decision making. In the typical development of…
Monte Carlo Tree Search with Scalable Simulation Periods for Continuously Running Tasks
Seydou Ba, Takuya Hiraoka, Takashi Onishi +2
Monte Carlo Tree Search (MCTS) is particularly adapted to domains where the potential actions can be represented as a tree of sequential decisions. For an effective action selectio…
Hierarchical Reinforcement Learning with Abductive Planning
Kazeto Yamamoto, Takashi Onishi, Yoshimasa Tsuruoka
One of the key challenges in applying reinforcement learning to real-life problems is that the amount of train-and-error required to learn a good policy increases drastically as th…
Translating MFM into FOL: towards plant operation planning
Shota Motoura, Kazeto Yamamoto, Shumpei Kubosawa +1
This paper proposes a method to translate multilevel flow modeling (MFM) into a first-order language (FOL), which enables the utilisation of logical techniques, such as inference e…