Search Results for author: Kai-Chun Hu

Found 4 papers, 0 papers with code

Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective

no code implementations26 Oct 2021 Nai-Chieh Huang, Ping-Chun Hsieh, Kuo-Hao Ho, Hsuan-Yu Yao, Kai-Chun Hu, Liang-Chun Ouyang, I-Chen Wu

Policy optimization is a fundamental principle for designing reinforcement learning algorithms, and one example is the proximal policy optimization algorithm with a clipped surrogate objective (PPO-Clip), which has been popularly used in deep reinforcement learning due to its simplicity and effectiveness.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning Trajectory Generation and Control for Aggressive Perching on Vertical Walls with Quadrotors

no code implementations4 Mar 2021 Chen-Huan Pi, Kai-Chun Hu, Yu-Ting Huang, Stone Cheng

This paper proposes a trajectory generating and tracking method for quadrotor perching that takes the advantages of reinforcement learning controller and traditional controller.

Robotics Systems and Control Systems and Control

Rethinking Deep Policy Gradients via State-Wise Policy Improvement

no code implementations NeurIPS Workshop ICBINB 2020 Kai-Chun Hu, Ping-Chun Hsieh, Ting Han Wei, I-Chen Wu

Deep policy gradient is one of the major frameworks in reinforcement learning, and it has been shown to improve parameterized policies across various tasks and environments.

Policy Gradient Methods Value prediction

Towards Combining On-Off-Policy Methods for Real-World Applications

no code implementations24 Apr 2019 Kai-Chun Hu, Chen-Huan Pi, Ting Han Wei, I-Chen Wu, Stone Cheng, Yi-Wei Dai, Wei-Yuan Ye

In this paper, we point out a fundamental property of the objective in reinforcement learning, with which we can reformulate the policy gradient objective into a perceptron-like loss function, removing the need to distinguish between on and off policy training.

OpenAI Gym Position

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