Zobrazeno 1 - 10
of 286
pro vyhledávání: '"Kobayashi, Taisuke"'
Autor:
Kobayashi, Taisuke
Experience replay (ER) used in (deep) reinforcement learning is considered to be applicable only to off-policy algorithms. However, there have been some cases in which ER has been applied for on-policy algorithms, suggesting that off-policyness might
Externí odkaz:
http://arxiv.org/abs/2402.10374
Autor:
Kobayashi, Taisuke
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 study addresses the problem of the most popular exception handling that t
Externí odkaz:
http://arxiv.org/abs/2308.12772
Autor:
Kobayashi, Taisuke
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 controller robust to noise and perturbation, which is useful for real-wo
Externí odkaz:
http://arxiv.org/abs/2303.04356
Autor:
Kobayashi, Taisuke
Publikováno v:
Results in Control and Optimization, 2023
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 bonuses have been designed to date, they are analogous to the depth-firs
Externí odkaz:
http://arxiv.org/abs/2212.10765
Autor:
Kobayashi, Taisuke, Fukumoto, Kota
Sampling-based model predictive control (MPC) can be applied to versatile robotic systems. However, the real-time control with it is a big challenge due to its unstable updates and poor convergence. This paper tackles this challenge with a novel deri
Externí odkaz:
http://arxiv.org/abs/2212.04298
Autor:
Kobayashi, Taisuke, Watanuki, Ryoma
Publikováno v:
Advanced Robotics, 2023
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 space. However, there is no established method for tuning the dimensio
Externí odkaz:
http://arxiv.org/abs/2208.03936
Autor:
Kobayashi, Taisuke
Publikováno v:
Results in Control and Optimization, 2023
Deep reinforcement learning (DRL) is one of the promising approaches for introducing robots into complicated environments. The recent remarkable progress of DRL stands on regularization of policy, which allows the policy to improve stably and efficie
Externí odkaz:
http://arxiv.org/abs/2203.09809
Autor:
Kobayashi, Taisuke
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 learning, a target network that slowly and asymptotically matches a main
Externí odkaz:
http://arxiv.org/abs/2202.12504
Autor:
Kobayashi, Taisuke
Publikováno v:
IROS 2022
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 the learning process and the sensitivity of the acquired policy to nois
Externí odkaz:
http://arxiv.org/abs/2202.07152
Publikováno v:
Neurocomputing 2023-08
With the increasing practicality of deep learning applications, practitioners are inevitably faced with datasets corrupted by noise from various sources such as measurement errors, mislabeling, and estimated surrogate inputs/outputs that can adversel
Externí odkaz:
http://arxiv.org/abs/2201.06714