Transformers are Sample-Efficient World ModelsDownload PDF

08 Oct 2022, 17:47 (modified: 09 Dec 2022, 14:31)Deep RL Workshop 2022Readers: Everyone
Keywords: deep learning, reinforcement learning, model-based reinforcement learning, world models, learning in imagination, transformers, discrete autoencoders, generative modeling, sequence modeling
TL;DR: We introduce a data-efficient agent that learns in a world model composed of a discrete autoencoder and an autoregressive Transformer.
Abstract: 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 codebase at https://github.com/eloialonso/iris.
Supplementary Material: zip
0 Replies

Loading