Deep reinforcement learning is a promising approach to learning policies in uncontrolled environments that do not require domain knowledge. Unfortunately, due to sample inefficiency, deep RL applications have primarily focused on simulated environments. In this work, we demonstrate that the recent advancements in machine learning algorithms and libraries combined with a carefully tuned robot controller lead to learning quadruped locomotion in only 20 minutes in the real world. We evaluate our approach on several indoor and outdoor terrains which are known to be challenging for classical model-based controllers. We observe the robot to be able to learn walking gait consistently on all of these terrains. Finally, we evaluate our design decisions in a simulated environment.

Online learning of Hawkes processes has received increasing attention in the last couple of years especially for modeling a network of actors. However, these works typically either model the rich interaction between the events or the latent cluster of the actors or the network structure between the actors. We propose to model the latent structure of the network of actors as well as their rich interaction across events for real-world settings of medical and financial applications.

Symbol detection is a fundamental and challenging problem in modern communication systems, e.g., multiuser multiple-input multiple-output (MIMO) setting. Iterative Soft Interference Cancellation (SIC) is a state-of-the-art method for this task and recently motivated data-driven neural network models, e.g. DeepSIC, that can deal with unknown non-linear channels. However, these neural network models require thorough timeconsuming training of the networks before applying, and is thus not readily suitable for highly dynamic channels in practice. We introduce an online training framework that can swiftly adapt to any changes in the channel. Our proposed framework unifies the recent deep unfolding approaches with the emerging generative adversarial networks (GANs) to capture any changes in the channel and quickly adjust the networks to maintain the top performance of the model. We demonstrate that our framework significantly outperforms recent neural network models on highly dynamic channels and even surpasses those on the static channel in our experiments.

One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is careful management of the agent's learning experiences, to learn (without forgetting) and build internal meta-models (of the tasks, environments, agents, and world). Generative replay (GR) is a biologically inspired replay mechanism that augments learning experiences with self-labelled examples drawn from an internal generative model that is updated over time. We present a version of GR for LRL that satisfies two desiderata: (a) Introspective density modelling of the latent representations of policies learned using deep RL, and (b) Model-free end-to-end learning. In this paper, we study three deep learning architectures for model-free GR, starting from a na\"ive GR and adding ingredients to achieve (a) and (b). We evaluate our proposed algorithms on three different scenarios comprising tasks from the Starcraft-2 and Minigrid domains. We report several key findings showing the impact of the design choices on quantitative metrics that include transfer learning, generalization to unseen tasks, fast adaptation after task change, performance wrt task expert, and catastrophic forgetting. We observe that our GR prevents drift in the features-to-action mapping from the latent vector space of a deep RL agent. We also show improvements in established lifelong learning metrics. We find that a small random replay buffer significantly increases the stability of training. Overall, we find that "hidden replay" (a well-known architecture for class-incremental classification) is the most promising approach that pushes the state-of-the-art in GR for LRL and observe that the architecture of the sleep model might be more important for improving performance than the types of replay used. Our experiments required only 6% of training samples to achieve 80-90% of expert performance in most Starcraft-2 scenarios.

In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. The challenge here lies in preserving the model's ability to effectively represent prior classes in the feature space, while adapting it to represent incoming new classes. We propose two distillation-based objectives for class incremental learning that leverage the structure of the feature space to maintain accuracy on previous classes, as well as enable learning the new classes. In our first objective, termed cross-space clustering (CSC), we propose to use the feature space structure of the previous model to characterize directions of optimization that maximally preserve the class: directions that all instances of a specific class should collectively optimize towards, and those that they should collectively optimize away from. Apart from minimizing forgetting, this indirectly encourages the model to cluster all instances of a class in the current feature space, and gives rise to a sense of herd-immunity, allowing all samples of a class to jointly combat the model from forgetting the class. Our second objective termed controlled transfer (CT) tackles incremental learning from an understudied perspective of inter-class transfer. CT explicitly approximates and conditions the current model on the semantic similarities between incrementally arriving classes and prior classes. This allows the model to learn classes in such a way that it maximizes positive forward transfer from similar prior classes, thus increasing plasticity, and minimizes negative backward transfer on dissimilar prior classes, whereby strengthening stability. We perform extensive experiments on two benchmark datasets, adding our method (CSCCT) on top of three prominent class-incremental learning methods. We observe consistent performance improvement on a variety of experimental settings.

Terahertz (THz) wireless networks are expected to catalyze the beyond fifth generation (B5G) era. However, due to the directional nature and the line-of-sight demand of THz links, as well as the ultra-dense deployment of THz networks, a number of challenges that the medium access control (MAC) layer needs to face are created. In more detail, the need of rethinking user association and resource allocation strategies by incorporating artificial intelligence (AI) capable of providing "real-time" solutions in complex and frequently changing environments becomes evident. Moreover, to satisfy the ultra-reliability and low-latency demands of several B5G applications, novel mobility management approaches are required. Motivated by this, this article presents a holistic MAC layer approach that enables intelligent user association and resource allocation, as well as flexible and adaptive mobility management, while maximizing systems' reliability through blockage minimization. In more detail, a fast and centralized joint user association, radio resource allocation, and blockage avoidance by means of a novel metaheuristic-machine learning framework is documented, that maximizes the THz networks performance, while minimizing the association latency by approximately three orders of magnitude. To support, within the access point (AP) coverage area, mobility management and blockage avoidance, a deep reinforcement learning (DRL) approach for beam-selection is discussed. Finally, to support user mobility between coverage areas of neighbor APs, a proactive hand-over mechanism based on AI-assisted fast channel prediction is~reported.

Rapid progress in machine learning for natural language processing has the potential to transform debates about how humans learn language. However, the learning environments and biases of current artificial learners and humans diverge in ways that weaken the impact of the evidence obtained from learning simulations. For example, today's most effective neural language models are trained on roughly one thousand times the amount of linguistic data available to a typical child. To increase the relevance of learnability results from computational models, we need to train model learners without significant advantages over humans. If an appropriate model successfully acquires some target linguistic knowledge, it can provide a proof of concept that the target is learnable in a hypothesized human learning scenario. Plausible model learners will enable us to carry out experimental manipulations to make causal inferences about variables in the learning environment, and to rigorously test poverty-of-the-stimulus-style claims arguing for innate linguistic knowledge in humans on the basis of speculations about learnability. Comparable experiments will never be possible with human subjects due to practical and ethical considerations, making model learners an indispensable resource. So far, attempts to deprive current models of unfair advantages obtain sub-human results for key grammatical behaviors such as acceptability judgments. But before we can justifiably conclude that language learning requires more prior domain-specific knowledge than current models possess, we must first explore non-linguistic inputs in the form of multimodal stimuli and multi-agent interaction as ways to make our learners more efficient at learning from limited linguistic input.

In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domain of machine learning, economics, and operations research. At first, we present the Meta-MFW algorithm achieving a $1/e$-regret of $O(\sqrt{T})$ at the cost of $T^{3/2}$ stochastic gradient evaluations per round. As far as we know, Meta-MFW is the first algorithm to obtain $1/e$-regret of $O(\sqrt{T})$ for the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set. Furthermore, in sharp contrast with ODC algorithm \citep{thang2021online}, Meta-MFW relies on the simple online linear oracle without discretization, lifting, or rounding operations. Considering the practical restrictions, we then propose the Mono-MFW algorithm, which reduces the per-function stochastic gradient evaluations from $T^{3/2}$ to 1 and achieves a $1/e$-regret bound of $O(T^{4/5})$. Next, we extend Mono-MFW to the bandit setting and propose the Bandit-MFW algorithm which attains a $1/e$-regret bound of $O(T^{8/9})$. To the best of our knowledge, Mono-MFW and Bandit-MFW are the first sublinear-regret algorithms to explore the one-shot and bandit setting for online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, respectively. Finally, we conduct numerical experiments on both synthetic and real-world datasets to verify the effectiveness of our methods.

Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting to new information, and improving their performance. In this work we study how to improve internet-driven conversational skills in such a learning framework. We collect deployment data, which we make publicly available, of human interactions, and collect various types of human feedback -- including binary quality measurements, free-form text feedback, and fine-grained reasons for failure. We then study various algorithms for improving from such feedback, including standard supervised learning, rejection sampling, model-guiding and reward-based learning, in order to make recommendations on which type of feedback and algorithms work best. We find the recently introduced Director model (Arora et al., '22) shows significant improvements over other existing approaches.

The convergence of 5G architecture and deep learning has gained a lot of research interests in both the fields of wireless communication and artificial intelligence. This is because deep learning technologies have been identified to be the potential driver of the 5G technologies, that make up the 5G architecture. Hence, there have been extensive surveys on the convergence of 5G architecture and deep learning. However, most of the existing survey papers mainly focused on how deep learning can converge with a specific 5G technology, thus, not covering the full spectrum of the 5G architecture. Although there is a recent survey paper that appears to be robust, a review of that paper shows that it is not well structured to specifically cover the convergence of deep learning and the 5G technologies. Hence, this paper provides a robust overview of the convergence of the key 5G technologies and deep learning. The challenges faced by such convergence are discussed. In addition, a brief overview of the future 6G architecture, and how it can converge with deep learning is also discussed.