Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration

Learning diverse and high-performance behaviors from a limited set of demonstrations is a grand challenge. Traditional imitation learning methods usually fail in this task because most of them are designed to learn one specific behavior even with multiple demonstrations. Therefore, novel techniques for quality diversity imitation learning are needed to solve the above challenge. This work introduces Wasserstein Quality Diversity Imitation Learning (WQDIL), which 1) improves the stability of imitation learning in the quality diversity setting with latent adversarial training based on a Wasserstein Auto-Encoder (WAE), and 2) mitigates a behavior-overfitting issue using a measure-conditioned reward function with a single-step archive exploration bonus. Empirically, our method significantly outperforms state-of-the-art IL methods, achieving near-expert or beyond-expert QD performance on the challenging continuous control tasks derived from MuJoCo environments.

Quality Diversity Imitation Learning

Imitation learning (IL) has shown great potential in various applications, such as robot control. However, traditional IL methods are usually designed to learn only one specific type of behavior since demonstrations typically correspond to a single expert. In this work, we introduce the first generic framework for Quality Diversity Imitation Learning (QD-IL), which enables the agent to learn a broad range of skills from limited demonstrations. Our framework integrates the principles of quality diversity with adversarial imitation learning (AIL) methods, and can potentially improve any inverse reinforcement learning (IRL) method. Empirically, our framework significantly improves the QD performance of GAIL and VAIL on the challenging continuous control tasks derived from Mujoco environments. Moreover, our method even achieves 2x expert performance in the most challenging Humanoid environment.

Intrinsic Reward Driven Imitation Learning via Generative Model

Imitation learning in a high-dimensional environment is challenging. Most inverse reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high-dimensional environment, e.g., Atari domain. To address this challenge, we propose a novel reward learning module to generate intrinsic reward signals via a generative model. Our generative method can perform better forward state transition and backward action encoding, which improves the module's dynamics modeling ability in the environment. Thus, our module provides the imitation agent both the intrinsic intention of the demonstrator and a better exploration ability, which is critical for the agent to outperform the demonstrator. Empirical results show that our method outperforms state-of-the-art IRL methods on multiple Atari games, even with one-life demonstration. Remarkably, our method achieves performance that is up to 5 times the performance of the demonstration.

Deep Adversarial Learning in Intrusion Detection: A Data Augmentation Enhanced Framework

Intrusion detection systems (IDSs) play an important role in identifying malicious attacks and threats in networking systems. As fundamental tools of IDSs, learning based classification methods have been widely employed. When it comes to detecting network intrusions in small sample sizes (e.g., emerging intrusions), the limited number and imbalanced proportion of training samples usually cause significant challenges in training supervised and semi-supervised classifiers. In this paper, we propose a general network intrusion detection framework to address the challenges of both \emph{data scarcity} and \emph{data imbalance}. The novelty of the proposed framework focuses on incorporating deep adversarial learning with statistical learning and exploiting learning based data augmentation. Given a small set of network intrusion samples, it first derives a Poisson-Gamma joint probabilistic generative model to generate synthesised intrusion data using Monte Carlo methods. Those synthesised data are then augmented by deep generative neural networks through adversarial learning. Finally, it adopts the augmented intrusion data to train supervised models for detecting network intrusions. Comprehensive experimental validations on KDD Cup 99 dataset show that the proposed framework outperforms the existing learning based IDSs in terms of improved accuracy, precision, recall, and F1-score.

How does Disagreement Help Generalization against Label Corruption?

Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters the state-of-the-art approach "Co-teaching" that cross-trains two deep neural networks using the small-loss trick. However, with the increase of epochs, two networks converge to a consensus and Co-teaching reduces to the self-training MentorNet. To tackle this issue, we propose a robust learning paradigm called Co-teaching+, which bridges the "Update by Disagreement" strategy with the original Co-teaching. First, two networks feed forward and predict all data, but keep prediction disagreement data only. Then, among such disagreement data, each network selects its small-loss data, but back propagates the small-loss data from its peer network and updates its own parameters. Empirical results on benchmark datasets demonstrate that Co-teaching+ is much superior to many state-of-the-art methods in the robustness of trained models.

Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of clean labels and then those of noisy labels. Therefore in this paper, we propose a new deep learning paradigm called Co-teaching for combating with noisy labels. Namely, we train two deep neural networks simultaneously, and let them teach each other given every mini-batch: firstly, each network feeds forward all data and selects some data of possibly clean labels; secondly, two networks communicate with each other what data in this mini-batch should be used for training; finally, each network back propagates the data selected by its peer network and updates itself. Empirical results on noisy versions of MNIST, CIFAR-10 and CIFAR-100 demonstrate that Co-teaching is much superior to the state-of-the-art methods in the robustness of trained deep models.

Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels

It is challenging to train deep neural networks robustly on the industrial-level data, since labels of such data are heavily noisy, and their label generation processes are normally agnostic. To handle these issues, by using the memorization effects of deep neural networks, we may train deep neural networks on the whole dataset only the first few iterations. Then, we may employ early stopping or the small-loss trick to train them on selected instances. However, in such training procedures, deep neural networks inevitably memorize some noisy labels, which will degrade their generalization. In this paper, we propose a meta algorithm called Pumpout to overcome the problem of memorizing noisy labels. By using scaled stochastic gradient ascent, Pumpout actively squeezes out the negative effects of noisy labels from the training model, instead of passively forgetting these effects. We leverage Pumpout to upgrade two representative methods: MentorNet and Backward Correction. Empirical results on benchmark datasets demonstrate that Pumpout can significantly improve the robustness of representative methods.