Generative Adversarial Neuroevolution for Control Behaviour Imitation

by   Maximilien Le Clei, et al.
Université de Montréal
Centre de recherche de l'IUGM

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


Task-Relevant Adversarial Imitation Learning

We show that a critical problem in adversarial imitation from high-dimen...

Neuroevolution of Recurrent Architectures on Control Tasks

Modern artificial intelligence works typically train the parameters of f...

Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems

Many tasks in practice require the collaboration of multiple agents thro...

Correlated Adversarial Imitation Learning

A novel imitation learning algorithm is introduced by applying a game-th...

Generative Adversarial Imitation Learning for Empathy-based AI

Generative adversarial imitation learning (GAIL) is a model-free algorit...

Co-Imitation: Learning Design and Behaviour by Imitation

The co-adaptation of robots has been a long-standing research endeavour ...

Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning

A common vision from science fiction is that robots will one day inhabit...

Please sign up or login with your details

Forgot password? Click here to reset