Neural Game Engine: Accurate learning of generalizable forward models from pixels
This addresses the need for accurate and scalable forward models in model-based reinforcement learning and related algorithms, though it is incremental by building on prior work like the Neural GPU.
The paper tackles the problem of learning generalizable forward models from pixel inputs for games, achieving competitive performance on 10 deterministic General Video Game AI games with many models learned perfectly in pixel and reward predictions.
Access to a fast and easily copied forward model of a game is essential for model-based reinforcement learning and for algorithms such as Monte Carlo tree search, and is also beneficial as a source of unlimited experience data for model-free algorithms. Learning forward models is an interesting and important challenge in order to address problems where a model is not available. Building upon previous work on the Neural GPU, this paper introduces the Neural Game Engine, as a way to learn models directly from pixels. The learned models are able to generalise to different size game levels to the ones they were trained on without loss of accuracy. Results on 10 deterministic General Video Game AI games demonstrate competitive performance, with many of the games models being learned perfectly both in terms of pixel predictions and reward predictions. The pre-trained models are available through the OpenAI Gym interface and are available publicly for future research here: \url{https://github.com/Bam4d/Neural-Game-Engine}