Yechan(Paul) Kim

2 Followers

ai reinforcement learning rl deep reinforcement learning 파이콘 2018 value based rl rainbow atari multi agent madrl pyconkr2018 pycon2018 gym deepmind game ai language grounding perception noisy network c51 distributional rl per prioritized experience replay multi step learning dueling dqn double dqn rl adventure 튜토리얼 multi agent deep reinforcement learning drl microsoft rl korea lva lvn vqa navigation 3d environment soft actor critic hierarchical reinforcement learning imitation learning nlp all you need diayn 강화학습 parser reasoning

Activity
About

Yechan(Paul) Kim

Presentations

pycon2018 "RL Adventure : DQN 부터 Rainbow DQN까지"

pyconkr 2018 RL_Adventure : Rainbow(value based Reinforcement Learning)

Diversity is all you need(DIAYN) : Learning Skills without a Reward Function

3D Environment : HomeNavigation

2018 global ai_bootcamp_seoul_HomeNavi(Reinforcement Learning, AI)

Multiagent Cooperative and Competition with Deep Reinforcement Learning

Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks

Neural module Network

강화학습과 LV&A 그리고 Navigation Agent

Likes

Explaining and harnessing adversarial examples (2015)