ED2: Environment Dynamics Decomposition World Models for Continuous Control

arXiv:2112.02817v2 Announce Type: replace
Abstract: Model-based reinforcement learning (MBRL) achieves significant sample efficiency in practice in comparison to model-free RL, but its performance is often limited by the existence of model prediction error. To reduce the model error, standard MBRL approaches train a single well-designed network to fit the entire environment dynamics, but this wastes rich information on multiple sub-dynamics which can be modeled separately, allowing us to construct the world model more accurately. In this paper, we propose the …

arxiv continuous control cs.ai cs.lg dynamics environment type world world models