Đăng nhập
thông tin chi tiết - Model-Based Reinforcement Learning Algorithm
TD-MPC2: Scalable, Robust World Models for Continuous Control
TD-MPC2 presents significant improvements over baselines in online RL tasks, achieving strong results with a single set of hyperparameters and demonstrating scalability.
大規模で堅牢な連続制御のための世界モデル TD-MPC2
TD-MPC2は、大規模で多様なデータセットから学習した世界モデルを用いて、104の連続制御タスクにおいて優れた性能を発揮する。
Giới thiệu
Sản Phẩm | Tài Nguyên
© 2024 by Linnk AI