Search Results for author: Kei Ota

Found 7 papers, 1 papers with code

OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching

1 code implementation9 Sep 2021 Hana Hoshino, Kei Ota, Asako Kanezaki, Rio Yokota

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious.

Training Larger Networks for Deep Reinforcement Learning

no code implementations16 Feb 2021 Kei Ota, Devesh K. Jha, Asako Kanezaki

Previous work has shown that this is mostly due to instability during training of deep RL agents when using larger networks.

Representation Learning

Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation

no code implementations14 Nov 2020 Kei Ota, Devesh K. Jha, Diego Romeres, Jeroen van Baar, Kevin A. Smith, Takayuki Semitsu, Tomoaki Oiki, Alan Sullivan, Daniel Nikovski, Joshua B. Tenenbaum

The physics engine augmented with the residual model is then used to control the marble in the maze environment using a model-predictive feedback over a receding horizon.

Deep Reactive Planning in Dynamic Environments

no code implementations31 Oct 2020 Kei Ota, Devesh K. Jha, Tadashi Onishi, Asako Kanezaki, Yusuke Yoshiyasu, Yoko SASAKI, Toshisada Mariyama, Daniel Nikovski

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution.

Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?

no code implementations ICML 2020 Kei Ota, Tomoaki Oiki, Devesh K. Jha, Toshisada Mariyama, Daniel Nikovski

We believe that stronger feature propagation together with larger networks (and thus larger search space) allows RL agents to learn more complex functions of states and thus improves the sample efficiency.

Decision Making

Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path

no code implementations3 Mar 2020 Kei Ota, Yoko SASAKI, Devesh K. Jha, Yusuke Yoshiyasu, Asako Kanezaki

Specifically, we train a deep convolutional network that can predict collision-free paths based on a map of the environment-- this is then used by a reinforcement learning algorithm to learn to closely follow the path.

Efficient Exploration

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning

no code implementations13 Mar 2019 Kei Ota, Devesh K. Jha, Tomoaki Oiki, Mamoru Miura, Takashi Nammoto, Daniel Nikovski, Toshisada Mariyama

Our experiments show that our RL agent trained with a reference path outperformed a model-free PID controller of the type commonly used on many robotic platforms for trajectory tracking.

Curriculum Learning Motion Planning

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