Traditional controllers have limitations as they rely on prior knowledge about the physics of the problem, require modeling of dynamics, and struggle to adapt to abnormal situations. Deep reinforcement learning has the potential to address these problems by learning optimal control policies through exploration in an environment. For safety-critical environments, it is impractical to explore randomly, and replacing conventional controllers with black-box models is also undesirable. Also, it is expensive in continuous state and action spaces, unless the search space is constrained. To address these challenges we propose a specialized deep residual policy safe reinforcement learning with a cycle of learning approach adapted for complex and continuous state-action spaces. Residual policy learning allows learning a hybrid control architecture where the reinforcement learning agent acts in synchronous collaboration with the conventional controller. The cycle of learning initiates the policy through the expert trajectory and guides the exploration around it. Further, the specialization through the input-output hidden Markov model helps to optimize policy that lies within the region of interest (such as abnormality), where the reinforcement learning agent is required and is activated. The proposed solution is validated on the Tennessee Eastman process control.

The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and thus enables sample-efficient learning. This becomes particularly beneficial in complex environments from high-dimensional state space such as pixels, where the goal is distant and the reward sparse. We introduce Forecaster, a deep hierarchical reinforcement learning approach which plans over high-level goals leveraging a temporally abstract world model. Forecaster learns an abstract model of its environment by modelling the transitions dynamics at an abstract level and training a world model on such transition. It then uses this world model to choose optimal high-level goals through a tree-search planning procedure. It additionally trains a low-level policy that learns to reach those goals. Our method not only captures building world models with longer horizons, but also, planning with such models in downstream tasks. We empirically demonstrate Forecaster's potential in both single-task learning and generalization to new tasks in the AntMaze domain.

Reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems. However, most RL algorithms lack an explicit method that would allow learning from contextual information. Humans use context to identify patterns and relations among elements in the environment, along with how to avoid making wrong actions. On the other hand, what may seem like an obviously wrong decision from a human perspective could take hundreds of steps for an RL agent to learn to avoid. This paper proposes a framework for discrete environments called Iota explicit context representation (IECR). The framework involves representing each state using contextual key frames (CKFs), which can then be used to extract a function that represents the affordances of the state; in addition, two loss functions are introduced with respect to the affordances of the state. The novelty of the IECR framework lies in its capacity to extract contextual information from the environment and learn from the CKFs' representation. We validate the framework by developing four new algorithms that learn using context: Iota deep Q-network (IDQN), Iota double deep Q-network (IDDQN), Iota dueling deep Q-network (IDuDQN), and Iota dueling double deep Q-network (IDDDQN). Furthermore, we evaluate the framework and the new algorithms in five discrete environments. We show that all the algorithms, which use contextual information, converge in around 40,000 training steps of the neural networks, significantly outperforming their state-of-the-art equivalents.

Resource allocation significantly impacts the performance of vehicle-to-everything (V2X) networks. Most existing algorithms for resource allocation are based on optimization or machine learning (e.g., reinforcement learning). In this paper, we explore resource allocation in a V2X network under the framework of federated reinforcement learning (FRL). On one hand, the usage of RL overcomes many challenges from the model-based optimization schemes. On the other hand, federated learning (FL) enables agents to deal with a number of practical issues, such as privacy, communication overhead, and exploration efficiency. The framework of FRL is then implemented by the inexact alternative direction method of multipliers (ADMM), where subproblems are solved approximately using policy gradients and accelerated by an adaptive step size calculated from their second moments. The developed algorithm, PASM, is proven to be convergent under mild conditions and has a nice numerical performance compared with some baseline methods for solving the resource allocation problem in a V2X network.

A large number of computational and scientific methods commonly require decomposing a sparse matrix into triangular factors as LU decomposition. A common problem faced during this decomposition is that even though the given matrix may be very sparse, the decomposition may lead to a denser triangular factors due to fill-in. A significant fill-in may lead to prohibitively larger computational costs and memory requirement during decomposition as well as during the solve phase. To this end, several heuristic sparse matrix reordering methods have been proposed to reduce fill-in before the decomposition. However, finding an optimal reordering algorithm that leads to minimal fill-in during such decomposition is known to be a NP-hard problem. A reinforcement learning based approach is proposed for this problem. The sparse matrix reordering problem is formulated as a single player game. More specifically, Monte-Carlo tree search in combination with neural network is used as a decision making algorithm to search for the best move in our game. The proposed method, Alpha Elimination is found to produce significantly lesser non-zeros in the LU decomposition as compared to existing state-of-the-art heuristic algorithms with little to no increase in overall running time of the algorithm.

In the realm of machine learning (ML) systems featuring client-host connections, the enhancement of privacy security can be effectively achieved through federated learning (FL) as a secure distributed ML methodology. FL effectively integrates cloud infrastructure to transfer ML models onto edge servers using blockchain technology. Through this mechanism, it guarantees the streamlined processing and data storage requirements of both centralized and decentralized systems, with an emphasis on scalability, privacy considerations, and cost-effective communication. In current FL implementations, data owners locally train their models, and subsequently upload the outcomes in the form of weights, gradients, and parameters to the cloud for overall model aggregation. This innovation obviates the necessity of engaging Internet of Things (IoT) clients and participants to communicate raw and potentially confidential data directly with a cloud center. This not only reduces the costs associated with communication networks but also enhances the protection of private data. This survey conducts an analysis and comparison of recent FL applications, aiming to assess their efficiency, accuracy, and privacy protection. However, in light of the complex and evolving nature of FL, it becomes evident that additional research is imperative to address lingering knowledge gaps and effectively confront the forthcoming challenges in this field. In this study, we categorize recent literature into the following clusters: privacy protection, resource allocation, case study analysis, and applications. Furthermore, at the end of each section, we tabulate the open areas and future directions presented in the referenced literature, affording researchers and scholars an insightful view of the evolution of the field.

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected and labeled datasets, which eliminates the time-consuming data collection in online RL. However, offline RL still bears a large burden of specifying/handcrafting extrinsic rewards for each transition in the offline data. As a remedy for the labor-intensive labeling, we propose to endow offline RL tasks with a few expert data and utilize the limited expert data to drive intrinsic rewards, thus eliminating the need for extrinsic rewards. To achieve that, we introduce \textbf{C}alibrated \textbf{L}atent g\textbf{U}idanc\textbf{E} (CLUE), which utilizes a conditional variational auto-encoder to learn a latent space such that intrinsic rewards can be directly qualified over the latent space. CLUE's key idea is to align the intrinsic rewards consistent with the expert intention via enforcing the embeddings of expert data to a calibrated contextual representation. We instantiate the expert-driven intrinsic rewards in sparse-reward offline RL tasks, offline imitation learning (IL) tasks, and unsupervised offline RL tasks. Empirically, we find that CLUE can effectively improve the sparse-reward offline RL performance, outperform the state-of-the-art offline IL baselines, and discover diverse skills from static reward-free offline data.

Robust Markov Decision Processes (MDPs) and risk-sensitive MDPs are both powerful tools for making decisions in the presence of uncertainties. Previous efforts have aimed to establish their connections, revealing equivalences in specific formulations. This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure (Ruszczy\'nski 2010), and establishes its equivalence with a class of regularized robust MDP (RMDP) problems, including the standard RMDP as a special case. Leveraging this equivalence, we further derive the policy gradient theorem for both problems, proving gradient domination and global convergence of the exact policy gradient method under the tabular setting with direct parameterization. This forms a sharp contrast to the Markov risk measure, known to be potentially non-gradient-dominant (Huang et al. 2021). We also propose a sample-based offline learning algorithm, namely the robust fitted-Z iteration (RFZI), for a specific regularized RMDP problem with a KL-divergence regularization term (or equivalently the risk-sensitive MDP with an entropy risk measure). We showcase its streamlined design and less stringent assumptions due to the equivalence and analyze its sample complexity.

One of the grand challenges of reinforcement learning is the ability to generalize to new tasks. However, general agents require a set of rich, diverse tasks to train on. Designing a'foundation environment' for such tasks is tricky - the ideal environment would support a range of emergent phenomena, an expressive task space, and fast runtime. To take a step towards addressing this research bottleneck, this work presents Powderworld, a lightweight yet expressive simulation environment running directly on the GPU. Within Powderworld, two motivating challenges distributions are presented, one for world-modelling and one for reinforcement learning. Each contains hand-designed test tasks to examine generalization. Experiments indicate that increasing the environment's complexity improves generalization for world models and certain reinforcement learning agents, yet may inhibit learning in high-variance environments. Powderworld aims to support the study of generalization by providing a source of diverse tasks arising from the same core rules. One of the grand challenges of reinforcement learning (RL), and of decision-making in general, is the ability to generalize to new tasks. RL agents have shown incredible performance on single task settings (Berner et al., 2019; Lillicrap et al., 2015; Mnih et al., 2013), yet frequently stumble when presented with unseen challenges. Single-task RL agents are largely overfit on the tasks they are trained on (Kirk et al., 2021), limiting their practical use. In contrast, a general agent, which can robustly perform well on a wide range of novel tasks, can then be adapted to solve downstream tasks and unseen challenges. General agents greatly depend on a diverse set of tasks to train on. Recent progress in deep learning has shown that as the amount of data increases, so do generalization capabilities of trained models (Brown et al., 2020; Ramesh et al., 2021; Bommasani et al., 2021; Radford et al., 2021). Agents trained on environments with domain randomization or procedural generation capabilities transfer better to unseen test tasks Cobbe et al. (2020); Tobin et al. (2017); Risi & Togelius (2020); Khalifa et al. (2020).

Reinforcement learning is a machine learning paradigm where an artificial agent learns the optimal behavior through interactions with a dynamic environment. Goals and purposes are explained to the agent via a scalar reward signal it receives after each interaction. Throughout the training process, the agent infers the behavior that maximizes cumulative reward, also called the return. To succeed in this task, the agent needs to explore the environment to understand which states and actions yield high rewards. On the other hand, the agent also has to exploit the rewards it has already received to adapt its behavior. This problem is known as the exploration and exploitation trade-off. This work was supported in part on Section 2 by the Strategic Project "Digital Business" within the framework of the Strategic Academic Leadership Program "Priority 2030" at the National University of Science and Technology (NUST) MISiS, in part by the Basic Research Program at the National Research University Higher School of Economics (HSE University), and in part by the Computational Resources of HPC Facilities at HSE University.