Abstract:Most robotic behaviours focus on either manipulation or locomotion, where tasks that require the integration of both, such as full-body throwing, remain under-explored. Throwing with a robot involves complex coordination between object manipulation and legged locomotion, which is crucial for advanced real-world interactions. This work investigates the challenge of full-body throwing in robotic systems and highlights the advantages of utilising the robot's entire body. We propose a deep reinforcement learning (RL) approach that leverages the robot's body to enhance throwing performance through a strategically designed curriculum to avoid local optima and sparse but informative reward functions to improve policy flexibility. The robot's body learns to generate additional momentum and fine-tune the projectile release velocity. Our full-body method achieves on average 47% greater throwing distance and 34% greater throwing accuracy than the arm alone, across two robot morphologies - an armed quadruped and a humanoid. We also extend our method to optimise robot stability during throws. The learned policy effectively generalises throwing to targets at any 3D point in space within a specified range, which has not previously been achieved and does so with human-level throwing accuracy. We successfully transferred this approach from simulation to a real robot using sim2real techniques, demonstrating its practical viability.
Abstract:The Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) is a state of the art evolutionary algorithm that leverages linkage learning to efficiently exploit problem structure. By identifying and preserving important building blocks during variation, GOMEA has shown promising performance on various optimization problems. In this paper, we provide the first runtime analysis of GOMEA on the concatenated trap function, a challenging benchmark problem that consists of multiple deceptive subfunctions. We derived an upper bound on the expected runtime of GOMEA with a truthful linkage model, showing that it can solve the problem in $O(m^{3}2^k)$ with high probability, where $m$ is the number of subfunctions and $k$ is the subfunction length. This is a significant speedup compared to the (1+1) EA, which requires $O(ln{(m)}(mk)^{k})$ expected evaluations.
Abstract:Crossover between neural networks is considered disruptive due to the strong functional dependency between connection weights. We propose a modularity-based linkage model at the weight level to preserve functionally dependent communities (building blocks) in neural networks during mixing. A proximity matrix is built by estimating the dependency between weights, then a community detection algorithm maximizing modularity is run on the graph described by such matrix. The resulting communities/groups of parameters are considered to be mutually independent and used as crossover masks in an optimal mixing EA. A variant is tested with an operator that neutralizes the permutation problem of neural networks to a degree. Experiments were performed on 8 and 10-bit parity problems as the intrinsic hierarchical nature of the dependencies in these problems are challenging to learn. The results show that our algorithm finds better, more functionally dependent linkage which leads to more successful crossover and better performance.
Abstract:Interest in reinforcement learning (RL) has recently surged due to the application of deep learning techniques, but these connectionist approaches are opaque compared with symbolic systems. Learning Classifier Systems (LCSs) are evolutionary machine learning systems that can be categorised as eXplainable AI (XAI) due to their rule-based nature. Michigan LCSs are commonly used in RL domains as the alternative Pittsburgh systems (e.g. SAMUEL) suffer from complex algorithmic design and high computational requirements; however they can produce more compact/interpretable solutions than Michigan systems. We aim to develop two novel Pittsburgh LCSs to address RL domains: PPL-DL and PPL-ST. The former acts as a "zeroth-level" system, and the latter revisits SAMUEL's core Monte Carlo learning mechanism for estimating rule strength. We compare our two Pittsburgh systems to the Michigan system XCS across deterministic and stochastic FrozenLake environments. Results show that PPL-ST performs on-par or better than PPL-DL and outperforms XCS in the presence of high levels of environmental uncertainty. Rulesets evolved by PPL-ST can achieve higher performance than those evolved by XCS, but in a more parsimonious and therefore more interpretable fashion, albeit with higher computational cost. This indicates that PPL-ST is an LCS well-suited to producing explainable policies in RL domains.
Abstract:Reinforcement learning (RL) is experiencing a resurgence in research interest, where Learning Classifier Systems (LCSs) have been applied for many years. However, traditional Michigan approaches tend to evolve large rule bases that are difficult to interpret or scale to domains beyond standard mazes. A Pittsburgh Genetic Fuzzy System (dubbed Fuzzy MoCoCo) is proposed that utilises both multiobjective and cooperative coevolutionary mechanisms to evolve fuzzy rule-based policies for RL environments. Multiobjectivity in the system is concerned with policy performance vs. complexity. The continuous state RL environment Mountain Car is used as a testing bed for the proposed system. Results show the system is able to effectively explore the trade-off between policy performance and complexity, and learn interpretable, high-performing policies that use as few rules as possible.
Abstract:Modularity is essential to many well-performing structured systems, as it is a useful means of managing complexity [8]. An analysis of modularity in neural networks produced by machine learning algorithms can offer valuable insight into the workings of such algorithms and how modularity can be leveraged to improve performance. However, this property is often overlooked in the neuroevolutionary literature, so the modular nature of many learning algorithms is unknown. This property was assessed on the popular algorithm "NeuroEvolution of Augmenting Topologies" (NEAT) for standard simulation benchmark control problems due to NEAT's ability to optimise network topology. This paper shows that NEAT networks seem to rapidly increase in modularity over time with the rate and convergence dependent on the problem. Interestingly, NEAT tends towards increasingly modular networks even when network fitness converges. It was shown that the ideal level of network modularity in the explored parameter space is highly dependent on other network variables, dispelling theories that modularity has a straightforward relationship to network performance. This is further proven in this paper by demonstrating that rewarding modularity directly did not improve fitness.
Abstract:In order to distinguish policies that prescribe good from bad actions in transient states, we need to evaluate the so-called bias of a policy from transient states. However, we observe that most (if not all) works in approximate discounting-free policy evaluation thus far are developed for estimating the bias solely from recurrent states. We therefore propose a system of approximators for the bias (specifically, its relative value) from transient and recurrent states. Its key ingredient is a seminorm LSTD (least-squares temporal difference), for which we derive its minimizer expression that enables approximation by sampling required in model-free reinforcement learning. This seminorm LSTD also facilitates the formulation of a general unifying procedure for LSTD-based policy value approximators. Experimental results validate the effectiveness of our proposed method.
Abstract:This paper presents a new Android malware detection method based on Graph Neural Networks (GNNs) with Jumping-Knowledge (JK). Android function call graphs (FCGs) consist of a set of program functions and their inter-procedural calls. Thus, this paper proposes a GNN-based method for Android malware detection by capturing meaningful intra-procedural call path patterns. In addition, a Jumping-Knowledge technique is applied to minimize the effect of the over-smoothing problem, which is common in GNNs. The proposed method has been extensively evaluated using two benchmark datasets. The results demonstrate the superiority of our approach compared to state-of-the-art approaches in terms of key classification metrics, which demonstrates the potential of GNNs in Android malware detection and classification.
Abstract:The standard ML methodology assumes that the test samples are derived from a set of pre-observed classes used in the training phase. Where the model extracts and learns useful patterns to detect new data samples belonging to the same data classes. However, in certain applications such as Network Intrusion Detection Systems, it is challenging to obtain data samples for all attack classes that the model will most likely observe in production. ML-based NIDSs face new attack traffic known as zero-day attacks, that are not used in the training of the learning models due to their non-existence at the time. In this paper, a zero-shot learning methodology has been proposed to evaluate the ML model performance in the detection of zero-day attack scenarios. In the attribute learning stage, the ML models map the network data features to distinguish semantic attributes from known attack (seen) classes. In the inference stage, the models are evaluated in the detection of zero-day attack (unseen) classes by constructing the relationships between known attacks and zero-day attacks. A new metric is defined as Zero-day Detection Rate, which measures the effectiveness of the learning model in the inference stage. The results demonstrate that while the majority of the attack classes do not represent significant risks to organisations adopting an ML-based NIDS in a zero-day attack scenario. However, for certain attack groups identified in this paper, such systems are not effective in applying the learnt attributes of attack behaviour to detect them as malicious. Further Analysis was conducted using the Wasserstein Distance technique to measure how different such attacks are from other attack types used in the training of the ML model. The results demonstrate that sophisticated attacks with a low zero-day detection rate have a significantly distinct feature distribution compared to the other attack classes.
Abstract:The tremendous numbers of network security breaches that have occurred in IoT networks have demonstrated the unreliability of current Network Intrusion Detection Systems (NIDSs). Consequently, network interruptions and loss of sensitive data have occurred which led to an active research area for improving NIDS technologies. During an analysis of related works, it was observed that most researchers aimed to obtain better classification results by using a set of untried combinations of Feature Reduction (FR) and Machine Learning (ML) techniques on NIDS datasets. However, these datasets are different in feature sets, attack types, and network design. Therefore, this paper aims to discover whether these techniques can be generalised across various datasets. Six ML models are utilised: a Deep Feed Forward, Convolutional Neural Network, Recurrent Neural Network, Decision Tree, Logistic Regression, and Naive Bayes. The detection accuracy of three Feature Extraction (FE) algorithms; Principal Component Analysis (PCA), Auto-encoder (AE), and Linear Discriminant Analysis (LDA) is evaluated using three benchmark datasets; UNSW-NB15, ToN-IoT and CSE-CIC-IDS2018. Although PCA and AE algorithms have been widely used, determining their optimal number of extracted dimensions has been overlooked. The results obtained indicate that there is no clear FE method or ML model that can achieve the best scores for all datasets. The optimal number of extracted dimensions has been identified for each dataset and LDA decreases the performance of the ML models on two datasets. The variance is used to analyse the extracted dimensions of LDA and PCA. Finally, this paper concludes that the choice of datasets significantly alters the performance of the applied techniques and we argue for the need for a universal (benchmark) feature set to facilitate further advancement and progress in this field of research.