General intelligence requires solving tasks across many domains. Current reinforcement learning algorithms carry this potential but are held back by the resources and knowledge required to tune them for new tasks. We present DreamerV3, a general and scalable algorithm based on world models that outperforms previous approaches across a wide range of domains with ﬁxed hyperparameters. These domains include continuous and discrete actions, visual and low-dimensional inputs, 2D and 3D worlds, different data budgets, reward frequencies
2023: Danijar Hafner, J. Pašukonis, Jimmy Ba, T. Lillicrap
To leave or reply to comments, please download free Podbean or
To leave or reply to comments, please download free Podbean App.