70 citations · 213 across the 23 of their papers we have counts for
23 papers
Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward
Taisuke Kobayashi
Robot control using reinforcement learning has become popular, but its learning process generally terminates halfway through an episode for safety and time-saving reasons. This stu…
Soft Actor-Critic Algorithm with Truly-satisfied Inequality Constraint
Taisuke Kobayashi
Soft actor-critic (SAC) in reinforcement learning is expected to be one of the next-generation robot control schemes. Its ability to maximize policy entropy would make a robotic co…
Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search
Taisuke Kobayashi
This paper introduces a novel method of adding intrinsic bonuses to task-oriented reward function in order to efficiently facilitate reinforcement learning search. While various bo…
Real-time Sampling-based Model Predictive Control based on Reverse Kullback-Leibler Divergence and Its Adaptive Acceleration
Taisuke Kobayashi, Kota Fukumoto
Sampling-based model predictive control (MPC) has the potential for use in a wide variety of robotic systems. However, its unstable updates and poor convergence render it unsuitabl…
Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model
Taisuke Kobayashi, Ryoma Watanuki
Extraction of low-dimensional latent space from high-dimensional observation data is essential to construct a real-time robot controller with a world model on the extracted latent…
Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio
Taisuke Kobayashi
Deep reinforcement learning (DRL) is one of the promising approaches for introducing robots into complicated environments. The recent remarkable progress of DRL stands on regulariz…
Consolidated Adaptive T-soft Update for Deep Reinforcement Learning
Taisuke Kobayashi
Demand for deep reinforcement learning (DRL) is gradually increased to enable robots to perform complex tasks, while DRL is known to be unstable. As a technique to stabilize its le…
L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning
Taisuke Kobayashi
This paper proposes a new regularization technique for reinforcement learning (RL) towards making policy and value functions smooth and stable. RL is known for the instability of t…
AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara
With the increasing practicality of deep learning applications, practitioners are inevitably faced with datasets corrupted by noise from various sources such as measurement errors,…
Impact of GPU uncertainty on the training of predictive deep neural networks
Maciej Pietrowski, Andrzej Gajda, Takuto Yamamoto +3
[retracted] We found out that the difference was dependent on the Chainer library, and does not replicate with another library (pytorch) which indicates that the results are probab…
Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
Behavioral cloning (BC) bears a high potential for safe and direct transfer of human skills to robots. However, demonstrations performed by human operators often contain noise or i…
Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics
Taisuke Kobayashi, Shingo Murata, Tetsunari Inamura
This paper presents a new data-driven framework for analyzing periodic physical human-robot interaction (pHRI) in latent state space. To elaborate human understanding and/or robot…
Hyperbolically-Discounted Reinforcement Learning on Reward-Punishment Framework
Taisuke Kobayashi
This paper proposes a new reinforcement learning with hyperbolic discounting. Combining a new temporal difference error with the hyperbolic discounting in recursive manner and rewa…
Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization
Taisuke Kobayashi
This paper addresses a new interpretation of the traditional optimization method in reinforcement learning (RL) as optimization problems using reverse Kullback-Leibler (KL) diverge…
Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures
Taisuke Kobayashi, Kenta Yoshizawa
Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimi…
Sample-efficient Gear-ratio Optimization for Biomechanical Energy Harvester
Taisuke Kobayashi, Yutaro Ikawa, Takamitsu Matsubara
The biomechanical energy harvester is expected to harvest the electric energies from human motions. A tradeoff between harvesting energy and keeping the user's natural movements sh…
Mirror-Descent Inverse Kinematics for Box-constrained Joint Space
Taisuke Kobayashi, Takanori Jin
To control humanoid robots, the reference pose of end effector(s) is planned in task space, then mapped into the reference joints by IK. By viewing that problem as approximate quad…
Deep unfolding-based output feedback control design for linear systems with input saturation
Koki Kobayashi, Masaki Ogura, Taisuke Kobayashi +1
In this paper, we propose a deep unfolding-based framework for the output feedback control of systems with input saturation. Although saturation commonly arises in several practica…
Proximal Policy Optimization with Relative Pearson Divergence
Taisuke Kobayashi
The recent remarkable progress of deep reinforcement learning (DRL) stands on regularization of policy for stable and efficient learning. A popular method, named proximal policy op…
t-Soft Update of Target Network for Deep Reinforcement Learning
Taisuke Kobayashi, Wendyam Eric Lionel Ilboudo
This paper proposes a new robust update rule of target network for deep reinforcement learning (DRL), to replace the conventional update rule, given as an exponential moving averag…
Adaptive and Multiple Time-scale Eligibility Traces for Online Deep Reinforcement Learning
Taisuke Kobayashi
Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follo…
Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems
Taisuke Kobayashi
This paper proposes a new optimizer for deep learning, named d-AmsGrad. In the real-world data, noise and outliers cannot be excluded from dataset to be used for learning robot ski…
TAdam: A Robust Stochastic Gradient Optimizer
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect the…