model-based2 Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing https://arxiv.org/abs/2103.04909 Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standar arxiv.org Introduction 2020 ICLR에서 발표.. 2024. 2. 3. Dream to Control : Learning Behaviors by Latent Imagination https://arxiv.org/abs/1912.01603 Dream to Control: Learning Behaviors by Latent Imagination Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for deriving behaviors arxiv.org Introduction 이 논문에서는 model-based RL 알고리.. 2024. 2. 1. 이전 1 다음
