Hanho RyuVideoGPT: Video Generation using VQ-VAE and TransformersVideoGPT, a video generation architecture that is a minimal adaptation of VQ-VAE and GPT architectures (transformers) for videosSep 9Sep 9
Hanho RyuInstructGPT: Training language models to follow instructions with human feedbackThis article is the summary of the paper “Training language models to follow instructions with human feedback” which introduced InstructGPTAug 24Aug 24
Hanho RyuMAML: Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksThis article is summary and review of the paper, “Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.”Aug 6Aug 6
Hanho RyuDecision Transformer: Reinforcement Learning via Sequence ModelingThis article is summary and review of the paper, “Decision Transformer: Reinforcement Learning via Sequence Modeling.”Aug 6Aug 6
Hanho RyuPPO: Proximal Policy Optimization AlgorithmsPPO, or Proximal Policy Optimization, is one of the most famous deep reinforcement learning algorithms.Jul 20Jul 20
Hanho RyuAlphaZero: Mastering Chess and Shogi by Self-Play with a General RLAlphaZero created a generalized, high-performance, and fast algorithm for chess, shogi, and Go with general reinforcement learnining.Jul 17Jul 17
Hanho Ryu[Paper Review] A3C: Asynchronous Methods for Deep Reinforcement LearningA3C, Asynchronous Advantage Actor-Critic. Summary of the paper “Asynchronous Methods for Deep Reinforcement Learning” with some details.Jul 9Jul 9
Hanho Ryu[Paper Review] Playing Atari with Deep Reinforcement Learning: DQNThis article is a summary of the paper “Playing Atari with Deep Reinforcement Learning” written by DeepMind Technologies.Jul 1Jul 1
Hanho Ryu[Paper Review] Going deeper with Image TransformersThis story is the review of the paper “Going deeper with Image Transformers (ICCV 21)”Jun 131Jun 131