Generative Adversarial Neuroevolution for Control Behaviour Imitation
This work addresses imitation learning for control tasks, offering a simple and generalizable neuroevolution approach that could be applied to complex real-world settings, though it is incremental as it adapts existing methods to a new domain.
The authors tackled behavior imitation in control tasks by proposing a co-evolutionary adversarial generation framework using deep neuroevolution, achieving scores as high as pre-trained agents on 8 OpenAI Gym tasks while closely following their trajectories.
There is a recent surge in interest for imitation learning, with large human video-game and robotic manipulation datasets being used to train agents on very complex tasks. While deep neuroevolution has recently been shown to match the performance of gradient-based techniques on various reinforcement learning problems, the application of deep neuroevolution techniques to imitation learning remains relatively unexplored. In this work, we propose to explore whether deep neuroevolution can be used for behaviour imitation on popular simulation environments. We introduce a simple co-evolutionary adversarial generation framework, and evaluate its capabilities by evolving standard deep recurrent networks to imitate state-of-the-art pre-trained agents on 8 OpenAI Gym state-based control tasks. Across all tasks, we find the final elite actor agents capable of achieving scores as high as those obtained by the pre-trained agents, all the while closely following their score trajectories. Our results suggest that neuroevolution could be a valuable addition to deep learning techniques to produce accurate emulation of behavioural agents. We believe that the generality and simplicity of our approach opens avenues for imitating increasingly complex behaviours in increasingly complex settings, e.g. human behaviour in real-world settings. We provide our source code, model checkpoints and results at github.com/MaximilienLC/gane.