
Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the imagination of a world model being one of the most prominent approaches. However, while virtually unlimited interaction with a simulated environment sounds appealing, the world model has to be accurate over extended periods of time. Motivated by the success of Transformers in sequence modeling tasks, we introduce IRIS , a data-efficient agent that learns in a world model composed of a discrete autoencoder and an autoregressive Transformer. With the equivalent of only two hours of gameplay in the Atari 100k benchmark, IRIS achieves a mean human normalized score of 1.046, and outperforms humans on 10 out of 26 games. Our approach sets a new state of the art for methods without lookahead search, and even surpasses MuZero. 2022: Vincent Micheli, Eloi Alonso, Franccois Fleuret https://arxiv.org/pdf/2209.00588v1.pdf
Comments (0)
To leave or reply to comments, please download free Podbean or
No Comments
To leave or reply to comments,
please download free Podbean App.