🏛 フィジカルAI 必読論文
ロボット基盤モデル・VLA・制御の礎となった論文を、分野別に日本語解説付きで。
収録 23 本。各ページに落合フォーマットの日本語要約と詳細解説を掲載しています。
基盤技術（ロボット基盤モデルが依拠） (3)
強化学習・制御・世界モデル (12)
- Playing Atari with Deep Reinforcement Learning被引用31k
- Proximal Policy Optimization Algorithms被引用30k
- Continuous control with deep reinforcement learning被引用16k
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks被引用15k
- Trust Region Policy Optimization
- Asynchronous Methods for Deep Reinforcement Learning
- Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
- Mastering Chess and Shogi by Self-Play
- Soft Actor-Critic
- World Models
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Mastering Diverse Domains through World Models
ロボット基盤モデル・VLA (8)
- A Generalist Agent
- RT-1: Robotics Transformer for Real-World Control at Scale
- PaLM-E: An Embodied Multimodal Language Model
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- π0: A Vision-Language-Action Flow Model for General Robot Control