Search Results for author:
Found 24 papers, 2 papers with code
Revisiting Experience Replayable Conditions
As a result, it is confirmed through numerical simulations that the proposed stabilization tricks make ER applicable to an advantage actor-critic, an on-policy algorithm.
Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward
Although this problem can be avoided by paying attention to the reward design, it is essential in practical use of TD learning to review the exception handling at termination.
Soft Actor-Critic Algorithm with Truly-satisfied Inequality Constraint
However, the priority of maximizing the policy entropy is automatically tuned in the current implementation, the rule of which can be interpreted as one for equality constraint, binding the policy entropy into its specified lower bound.
Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search
This paper introduces a novel method of adding intrinsic bonuses to task-oriented reward function in order to efficiently facilitate reinforcement learning search.
Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model
We experimentally verified the benefits of the sparsification by the proposed method that it can easily find the necessary and sufficient six dimensions for a reaching task with a mobile manipulator that requires a six-dimensional state space.
Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio
However, the density ratio is asymmetric for its center, and the possible error scale from its center, which should be close to the threshold, would depend on how the baseline policy is given.
Consolidated Adaptive T-soft Update for Deep Reinforcement Learning
Recently, T-soft update has been proposed as a noise-robust update rule for the target network and has contributed to improving the DRL performance.
L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning
RL is known for the instability of the learning process and the sensitivity of the acquired policy to noise.
AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization
In this paper, we propose AdaTerm, a novel approach that incorporates the Student's t-distribution to derive not only the first-order moment but also all the associated statistics.
Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning
On the other hand, the concept of personal mobility is also getting popular, and its autonomous driving specialized for individual drivers is expected for a new step.
Impact of GPU uncertainty on the training of predictive deep neural networks
GPU-specific computational processing is more indeterminate than that by CPUs, and hardware-derived uncertainties, which are often considered obstacles that need to be eliminated, might, in some cases, be successfully incorporated into the training of deep neural networks.
Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning
In order to allow the imitators to effectively learn from imperfect demonstrations, we propose to employ the robust t-momentum optimization algorithm.
Motion Illusion-like Patterns Extracted from Photo and Art Images Using Predictive Deep Neural Networks
In our previous study, we successfully reproduced the illusory motion of the rotating snakes illusion using deep neural networks incorporating predictive coding theory.
Artificial Perception Meets Psychophysics, Revealing a Fundamental Law of Illusory Motion
Rotating Snakes is a visual illusion in which a stationary design is perceived to move dramatically.
Hyperbolically-Discounted Reinforcement Learning on Reward-Punishment Framework
This paper proposes a new reinforcement learning with hyperbolic discounting.
Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization
This paper addresses a new interpretation of the traditional optimization method in reinforcement learning (RL) as optimization problems using reverse Kullback-Leibler (KL) divergence, and derives a new optimization method using forward KL divergence, instead of reverse KL divergence in the optimization problems.
Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures
To alleviate this drawback of the FB controllers, feedback error learning integrates one of them with a feedforward (FF) controller.
Deep unfolding-based output feedback control design for linear systems with input saturation
In this paper, we propose a deep unfolding-based framework for the output feedback control of systems with input saturation.
Proximal Policy Optimization with Relative Pearson Divergence
PPO clips density ratio of the latest and baseline policies with a threshold, while its minimization target is unclear.
t-Soft Update of Target Network for Deep Reinforcement Learning
The problem with its conventional update rule is the fact that all the parameters are smoothly copied with the same speed from the main network, even when some of them are trying to update toward the wrong directions.
Adaptive and Multiple Time-scale Eligibility Traces for Online Deep Reinforcement Learning
The eligibility traces method is well known as an online learning technique for improving sample efficiency in traditional reinforcement learning with linear regressors rather than DRL.
Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems
In the real-world data, noise and outliers cannot be excluded from dataset to be used for learning robot skills.
q-VAE for Disentangled Representation Learning and Latent Dynamical Systems
In the proposed method, a standard VAE is employed to statistically extract latent space hidden in sampled data, and this latent space helps make robots controllable in feasible computational time and cost.
TAdam: A Robust Stochastic Gradient Optimizer
Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain.
