Proximal Policy Gradient: PPO with Policy Gradient

no code implementations • 20 Oct 2020 • Ju-Seung Byun, Byungmoon Kim, Huamin Wang

In this paper, we propose a new algorithm PPG (Proximal Policy Gradient), which is close to both VPG (vanilla policy gradient) and PPO (proximal policy optimization).

OpenAI Gym

Training a Constrained Natural Media Painting Agent using Reinforcement Learning

no code implementations • 25 Sep 2019 • Biao Jia, Jonathan Brandt, Radomir Mech, Ning Xu, Byungmoon Kim, Dinesh Manocha

We present a novel approach to train a natural media painting using reinforcement learning.

reinforcement-learning Reinforcement Learning +1

LPaintB: Learning to Paint from Self-Supervision

no code implementations • 17 Jun 2019 • Biao Jia, Jonathan Brandt, Radomir Mech, Byungmoon Kim, Dinesh Manocha

We present a novel reinforcement learning-based natural media painting algorithm.

reinforcement-learning Reinforcement Learning +2

PaintBot: A Reinforcement Learning Approach for Natural Media Painting

no code implementations • 3 Apr 2019 • Biao Jia, Chen Fang, Jonathan Brandt, Byungmoon Kim, Dinesh Manocha

Action selection is guided by a given reference image, which the agent attempts to replicate subject to the limitations of the action space and the agent's learned policy.

reinforcement-learning Reinforcement Learning +1

Learning to Sketch with Deep Q Networks and Demonstrated Strokes

no code implementations • 14 Oct 2018 • Tao Zhou, Chen Fang, Zhaowen Wang, Jimei Yang, Byungmoon Kim, Zhili Chen, Jonathan Brandt, Demetri Terzopoulos

Doodling is a useful and common intelligent skill that people can learn and master.

Q-Learning