In-Person Poster presentation / top 5% paper
Transformers are Sample-Efficient World Models
Vincent Micheli · Eloi Alonso · François Fleuret
MH1-2-3-4 #117
Keywords: [ Reinforcement Learning ] [ reinforcement learning ] [ World Models ] [ learning in imagination ] [ discrete autoencoders ] [ deep learning ] [ model-based reinforcement learning ] [ transformers ] [ sequence modeling ] [ generative modeling ]
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, setting a new state of the art for methods without lookahead search. To foster future research on Transformers and world models for sample-efficient reinforcement learning, we release our code and models at https://github.com/eloialonso/iris.