Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to sequential decision-making tasks, however, it is difficult to properly design such a pretraining approach that can cope with both high-dimensional perceptual information and the complexity of sequential control over long interaction horizons. The challenge becomes combinatorially more complex if we want to pretrain representations amenable to a large variety of tasks. To tackle this problem, in this work, we formulate a general pretraining-finetuning pipeline for sequential decision making, under which we propose a generic pretraining framework \textit{Self-supervised Multi-task pretrAining with contRol Transformer (SMART)}. By systematically investigating pretraining regimes, we carefully design a Control Transformer (CT) coupled with a novel control-centric pretraining objective in a self-supervised manner. SMART encourages the representation to capture the common essential information relevant to short-term control and long-term control, which is transferrable across tasks. We show by extensive experiments in DeepMind Control Suite that SMART significantly improves the learning efficiency among seen and unseen downstream tasks and domains under different learning scenarios including Imitation Learning (IL) and Reinforcement Learning (RL). Benefiting from the proposed control-centric objective, SMART is resilient to distribution shift between pretraining and finetuning, and even works well with low-quality pretraining datasets that are randomly collected.

Recent research has employed reinforcement learning (RL) algorithms to optimize long-term user engagement in recommender systems, thereby avoiding common pitfalls such as user boredom and filter bubbles. They capture the sequential and interactive nature of recommendations, and thus offer a principled way to deal with long-term rewards and avoid myopic behaviors. However, RL approaches are intractable in the slate recommendation scenario - where a list of items is recommended at each interaction turn - due to the combinatorial action space. In that setting, an action corresponds to a slate that may contain any combination of items. While previous work has proposed well-chosen decompositions of actions so as to ensure tractability, these rely on restrictive and sometimes unrealistic assumptions. Instead, in this work we propose to encode slates in a continuous, low-dimensional latent space learned by a variational auto-encoder. Then, the RL agent selects continuous actions in this latent space, which are ultimately decoded into the corresponding slates. By doing so, we are able to (i) relax assumptions required by previous work, and (ii) improve the quality of the action selection by modeling full slates instead of independent items, in particular by enabling diversity. Our experiments performed on a wide array of simulated environments confirm the effectiveness of our generative modeling of slates over baselines in practical scenarios where the restrictive assumptions underlying the baselines are lifted. Our findings suggest that representation learning using generative models is a promising direction towards generalizable RL-based slate recommendation.

The quality of the video stream is key to neural network-based video analytics. However, low-quality video is inevitably collected by existing surveillance systems because of poor quality cameras or over-compressed/pruned video streaming protocols, e.g., as a result of upstream bandwidth limit. To address this issue, existing studies use quality enhancers (e.g., neural super-resolution) to improve the quality of videos (e.g., resolution) and eventually ensure inference accuracy. Nevertheless, directly applying quality enhancers does not work in practice because it will introduce unacceptable latency. In this paper, we present AccDecoder, a novel accelerated decoder for real-time and neural-enhanced video analytics. AccDecoder can select a few frames adaptively via Deep Reinforcement Learning (DRL) to enhance the quality by neural super-resolution and then up-scale the unselected frames that reference them, which leads to 6-21% accuracy improvement. AccDecoder provides efficient inference capability via filtering important frames using DRL for DNN-based inference and reusing the results for the other frames via extracting the reference relationship among frames and blocks, which results in a latency reduction of 20-80% than baselines.

The last decade, (2012 - 2022), saw an unprecedented advance in machine learning (ML) techniques, particularly deep learning (DL). As a result of the proven capabilities of DL, a large amount of work has been presented and studied in almost every field. Since 2012, when the convolution neural networks have been reintroduced in the context of \textit{ImagNet} competition, DL continued to achieve superior performance in many challenging tasks and problems. Wireless communications, in general, and medium access control (MAC) techniques, in particular, were among the fields that were heavily affected by this improvement. MAC protocols play a critical role in defining the performance of wireless communication systems. At the same time, the community lacks a comprehensive survey that collects, analyses, and categorizes the recent work in ML-inspired MAC techniques. In this work, we fill this gap by surveying a long line of work in this era. We solidify the impact of machine learning on wireless MAC protocols. We provide a comprehensive background to the widely adopted MAC techniques, their design issues, and their taxonomy, in connection with the famous application domains. Furthermore, we provide an overview of the ML techniques that have been considered in this context. Finally, we augment our work by proposing some promising future research directions and open research questions that are worth further investigation.

Urban air mobility is the new mode of transportation aiming to provide a fast and secure way of travel by utilizing the low-altitude airspace. This goal cannot be achieved without the implementation of new flight regulations which can assure safe and efficient allocation of flight paths to a large number of vertical takeoff/landing aerial vehicles. Such rules should also allow estimating the effective capacity of the low-altitude airspace for planning purposes. Path planning is a vital subject in urban air mobility which could enable a large number of UAVs to fly simultaneously in the airspace without facing the risk of collision. Since urban air mobility is a novel concept, authorities are still working on the redaction of new flight rules applicable to urban air mobility. In this study, an autonomous UAV path planning framework is proposed using a deep reinforcement learning approach and a deep deterministic policy gradient algorithm. The objective is to employ a self-trained UAV to reach its destination in the shortest possible time in any arbitrary environment by adjusting its acceleration. It should avoid collisions with any dynamic or static obstacles and avoid entering prior permission zones existing on its path. The reward function is the determinant factor in the training process. Thus, two different reward function compositions are compared and the chosen composition is deployed to train the UAV by coding the RL algorithm in python. Finally, numerical simulations investigated the success rate of UAVs in different scenarios providing an estimate of the effective airspace capacity.

The Flexible Job-shop Scheduling Problem (FJSP) is an important combinatorial optimization problem that arises in manufacturing and service settings. FJSP is composed of two subproblems, an assignment problem that assigns tasks to machines, and a scheduling problem that determines the starting times of tasks on their chosen machines. Solving FJSP instances of realistic size and composition is an ongoing challenge even under simplified, deterministic assumptions. Motivated by the inevitable randomness and uncertainties in supply chains, manufacturing, and service operations, this paper investigates the potential of using a deep learning framework to generate fast and accurate approximations for FJSP. In particular, this paper proposes a two-stage learning framework 2SLFJSP that explicitly models the hierarchical nature of FJSP decisions, uses a confidence-aware branching scheme to generate appropriate instances for the scheduling stage from the assignment predictions and leverages a novel symmetry-breaking formulation to improve learnability. 2SL-FJSP is evaluated on instances from the FJSP benchmark library. Results show that 2SL-FJSP can generate high-quality solutions in milliseconds, outperforming a state-of-the-art reinforcement learning approach recently proposed in the literature, and other heuristics commonly used in practice.

We propose to use reinforcement learning to inform transformer-based contextualized link prediction models by providing paths that are most useful for predicting the correct answer. This is in contrast to previous approaches, that either used reinforcement learning (RL) to directly search for the answer, or based their prediction on limited or randomly selected context. Our experiments on WN18RR and FB15k-237 show that contextualized link prediction models consistently outperform RL-based answer search, and that additional improvements (of up to 13.5% MRR) can be gained by combining RL with a link prediction model. The PyTorch implementation of the RL agent is available at https://github.com/marina-sp/reinform

Achieving convergence of multiple learning agents in general $N$-player games is imperative for the development of safe and reliable machine learning (ML) algorithms and their application to autonomous systems. Yet it is known that, outside the bounds of simple two-player games, convergence cannot be taken for granted. To make progress in resolving this problem, we study the dynamics of smooth Q-Learning, a popular reinforcement learning algorithm which quantifies the tendency for learning agents to explore their state space or exploit their payoffs. We show a sufficient condition on the rate of exploration such that the Q-Learning dynamics is guaranteed to converge to a unique equilibrium in any game. We connect this result to games for which Q-Learning is known to converge with arbitrary exploration rates, including weighted Potential games and weighted zero sum polymatrix games. Finally, we examine the performance of the Q-Learning dynamic as measured by the Time Averaged Social Welfare, and comparing this with the Social Welfare achieved by the equilibrium. We provide a sufficient condition whereby the Q-Learning dynamic will outperform the equilibrium even if the dynamics do not converge.

Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically independent of motion planning. For example, traditional object detection is passive: it operates only on the images it receives. However, we have a chance to improve the results if we allow planning to consume detection signals and move the robot to collect views that maximize the quality of the results. In this paper, we use reinforcement learning (RL) methods to control the robot in order to obtain images that maximize the detection quality. Specifically, we propose using a Decision Transformer with online fine-tuning, which first optimizes the policy with a pre-collected expert dataset and then improves the learned policy by exploring better solutions in the environment. We evaluate the performance of proposed method on an interactive dataset collected from an indoor scenario simulator. Experimental results demonstrate that our method outperforms all baselines, including expert policy and pure offline RL methods. We also provide exhaustive analyses of the reward distribution and observation space.

Reinforcement learning (RL) is a paradigm of AI methodologies in which an agent learns to interact with its environment in order to maximize the expectation of reward signals received from its environment. Unlike supervised learning, in which the agent is given labeled examples and learns to predict an output based on input, RL involves the agent actively taking actions in its environment and receiving feedback in the form of rewards or punishments. This feedback is used to adjust the agent's behavior and improve its performance over time. RL has been applied to a wide range of domains, including robotics, natural language processing, and finance. In the gaming industry, RL has been used to develop advanced game-playing agents, such as the AlphaGo [1] algorithm that defeated a human champion in the board game Go.