TD-MPC2: Scalable, Robust World Models for Continuous Control
원문 초록
TD-MPC is a model-based reinforcement learning (RL) algorithm that performs local trajectory optimization in the latent space of a learned implicit (decoder-free) world model. In this work, we present TD-MPC2: a series of improvements upon the TD-MPC algorithm. We demonstrate that TD-MPC2 improves significantly over baselines across 104 online RL tasks spanning 4 diverse task domains, achieving consistently strong results with a single set of hyperparameters. We further show that agent capabilities increase with model and data size, and successfully train a single 317M parameter agent to perform 80 tasks across multiple task domains, embodiments, and action spaces. We conclude with an account of lessons, opportunities, and risks associated with large TD-MPC2 agents. Explore videos, models, data, code, and more at https://tdmpc2.com
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)
CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum
rQdia: Regularizing Q-Value Distributions With Image Augmentation
Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute
토론
이 논문과 연결된 포럼 글이 아직 없습니다.