Jaewoo Song's picture

2

Jaewoo Song

devjwsong

https://songstudio.info

devjwsong

AI & ML interests

Machine Learning, Deep Learning, Natural Language Processing, Natural Language Generation, Conversational AI, Dialogue Systems

Recent Activity

upvoted an article 5 days ago

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

upvoted an article 6 months ago

Mixture of Experts Explained

updated a model over 1 year ago

devjwsong/gpt2-open-domain-dialogue

View all activity

Organizations

None yet

models 15

devjwsong/gpt2-open-domain-dialogue

Text Generation • Updated Jun 4, 2024 • 3 • 1

devjwsong/reinforce-Pixelcopter-PLE-v0

Reinforcement Learning • Updated May 25, 2024

devjwsong/ppo-a2c-LunarLander-v2

Reinforcement Learning • Updated May 25, 2024

devjwsong/rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning • Updated May 23, 2024

devjwsong/ppo-CartPole-v1

Reinforcement Learning • Updated May 23, 2024

devjwsong/poca-SoccerTwos

Reinforcement Learning • Updated May 16, 2024

devjwsong/a2c-PandaReachDense-v3

Reinforcement Learning • Updated May 15, 2024

devjwsong/ppo-Pyramid

Reinforcement Learning • Updated May 14, 2024 • 1

devjwsong/ppo-SnowballTarget

Reinforcement Learning • Updated May 14, 2024 • 6

devjwsong/reinforce-CartPole-v1

Reinforcement Learning • Updated Apr 18, 2024

datasets 0

None public yet