Stochastic multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a stochastic reward. Within the context of best-arm identification (BAI) problems, the goal of the agent lies in finding the optimal arm, i.e., the one with highest expected reward, as accurately and efficiently as possible. Nevertheless, the sequential interaction protocol of classical BAI problems, where the agent has complete control over the arm being pulled at each round, does not effectively model several decision-making problems of interest (e.g., off-policy learning, partially controllable environments, and human feedback). For this reason, in this work, we propose a novel strict generalization of the classical BAI problem that we refer to as best-arm identification under mediators' feedback (BAI-MF). More specifically, we consider the scenario in which the learner has access to a set of mediators, each of which selects the arms on the agent's behalf according to a stochastic and possibly unknown policy. The mediator, then, communicates back to the agent the pulled arm together with the observed reward. In this setting, the agent's goal lies in sequentially choosing which mediator to query to identify with high probability the optimal arm while minimizing the identification time, i.e., the sample complexity. To this end, we first derive and analyze a statistical lower bound on the sample complexity specific to our general mediator feedback scenario. Then, we propose a sequential decision-making strategy for discovering the best arm under the assumption that the mediators' policies are known to the learner. As our theory verifies, this algorithm matches the lower bound both almost surely and in expectation. Finally, we extend these results to cases where the mediators' policies are unknown to the learner obtaining comparable results.

In Reinforcement Learning (RL), the goal of agents is to discover an optimal policy that maximizes the expected cumulative rewards. This objective may also be viewed as finding a policy that optimizes a linear function of its state-action occupancy measure, hereafter referred as Linear RL. However, many supervised and unsupervised RL problems are not covered in the Linear RL framework, such as apprenticeship learning, pure exploration and variational intrinsic control, where the objectives are non-linear functions of the occupancy measures. RL with non-linear utilities looks unwieldy, as methods like Bellman equation, value iteration, policy gradient, dynamic programming that had tremendous success in Linear RL, fail to trivially generalize. In this paper, we derive the policy gradient theorem for RL with general utilities. The policy gradient theorem proves to be a cornerstone in Linear RL due to its elegance and ease of implementability. Our policy gradient theorem for RL with general utilities shares the same elegance and ease of implementability. Based on the policy gradient theorem derived, we also present a simple sample-based algorithm. We believe our results will be of interest to the community and offer inspiration to future works in this generalized setting.

(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic system models that are sufficiently accurate in all relevant state-space regions. These models must also be computationally cheap enough to ensure real-time tractability. Data-driven surrogate models for mechanistic models can be used to reduce the computational burden of (e)NMPC; however, such models are typically trained by system identification for maximum average prediction accuracy on simulation samples and perform suboptimally as part of actual (e)NMPC. We present a method for end-to-end reinforcement learning of dynamic surrogate models for optimal performance in (e)NMPC applications, resulting in predictive controllers that strike a favorable balance between control performance and computational demand. We validate our method on two applications derived from an established nonlinear continuous stirred-tank reactor model. We compare the controller performance to that of MPCs utilizing models trained by the prevailing maximum prediction accuracy paradigm, and model-free neural network controllers trained using reinforcement learning. We show that our method matches the performance of the model-free neural network controllers while consistently outperforming models derived from system identification. Additionally, we show that the MPC policies can react to changes in the control setting without retraining.

Safe and optimal controller synthesis for switched-controlled hybrid systems, which combine differential equations and discrete changes of the system's state, is known to be intricately hard. Reinforcement learning has been leveraged to construct near-optimal controllers, but their behavior is not guaranteed to be safe, even when it is encouraged by reward engineering. One way of imposing safety to a learned controller is to use a shield, which is correct by design. However, obtaining a shield for non-linear and hybrid environments is itself intractable. In this paper, we propose the construction of a shield using the so-called barbaric method, where an approximate finite representation of an underlying partition-based two-player safety game is extracted via systematically picked samples of the true transition function. While hard safety guarantees are out of reach, we experimentally demonstrate strong statistical safety guarantees with a prototype implementation and Uppaal Stratego. Furthermore, we study the impact of the synthesized shield when applied as either a pre-shield (applied before learning a controller) or a post-shield (only applied after learning a controller). We experimentally demonstrate superiority of the pre-shielding approach. We apply our technique on a range of case studies, including two industrial examples, and further study post-optimization of the post-shielding approach.

In recent years, Reinforcement Learning (RL) has emerged as a powerful tool for solving a wide range of problems, including decision-making and genomics. The exponential growth of raw genomic data over the past two decades has exceeded the capacity of manual analysis, leading to a growing interest in automatic data analysis and processing. RL algorithms are capable of learning from experience with minimal human supervision, making them well-suited for genomic data analysis and interpretation. One of the key benefits of using RL is the reduced cost associated with collecting labeled training data, which is required for supervised learning. While there have been numerous studies examining the applications of Machine Learning (ML) in genomics, this survey focuses exclusively on the use of RL in various genomics research fields, including gene regulatory networks (GRNs), genome assembly, and sequence alignment. We present a comprehensive technical overview of existing studies on the application of RL in genomics, highlighting the strengths and limitations of these approaches. We then discuss potential research directions that are worthy of future exploration, including the development of more sophisticated reward functions as RL heavily depends on the accuracy of the reward function, the integration of RL with other machine learning techniques, and the application of RL to new and emerging areas in genomics research. Finally, we present our findings and conclude by summarizing the current state of the field and the future outlook for RL in genomics.

Maneuver decision-making can be regarded as a Markov decision process and can be address by reinforcement learning. However, original reinforcement learning algorithms can hardly solve the maneuvering decision-making problem. One reason is that agents use random actions in the early stages of training, which makes it difficult to get rewards and learn how to make effective decisions. To address this issue, a method based on proximal policy optimization and Monte Carlo tree search is proposed. The method uses proximal policy optimization to train the agent, and regards the results of air combat as targets to train the value network. Then, based on the value network and the visit count of each node, Monte Carlo tree search is used to find the actions with more expected returns than random actions, which can improve the training performance. The ablation studies and simulation experiments indicate that agents trained by the proposed method can make different decisions according to different states, which demonstrates that the method can solve the maneuvering decision problem that the original reinforcement learning algorithm cannot solve.

Deep reinforcement learning (DRL) has seen remarkable success in the control of single robots. However, applying DRL to robot swarms presents significant challenges. A critical challenge is non-stationarity, which occurs when two or more robots update individual or shared policies concurrently, thereby engaging in an interdependent training process with no guarantees of convergence. Circumventing non-stationarity typically involves training the robots with global information about other agents' states and/or actions. In contrast, in this paper we explore how to remove the need for global information. We pose our problem as a Partially Observable Markov Decision Process, due to the absence of global knowledge on other agents. Using collective transport as a testbed scenario, we study two approaches to multi-agent training. In the first, the robots exchange no messages, and are trained to rely on implicit communication through push-and-pull on the object to transport. In the second approach, we introduce Global State Prediction (GSP), a network trained to forma a belief over the swarm as a whole and predict its future states. We provide a comprehensive study over four well-known deep reinforcement learning algorithms in environments with obstacles, measuring performance as the successful transport of the object to the goal within a desired time-frame. Through an ablation study, we show that including GSP boosts performance and increases robustness when compared with methods that use global knowledge.

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention mechanism and the large feedforward network in Transformers limit their ability to handle long sequences, thereby creating challenges for tasks involving multiple long sequences or long-term dependencies. We present a distinct approach, Blockwise Parallel Transformer (BPT), that leverages blockwise computation of self-attention and feedforward network fusion to minimize memory costs. By processing longer input sequences while maintaining memory efficiency, BPT enables training sequences 32 times longer than vanilla Transformers and up to 4 times longer than previous memory-efficient methods. Extensive experiments on language modeling and reinforcement learning tasks demonstrate the effectiveness of BPT in reducing memory requirements and improving performance.

We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q-learning with reward machines for stochastic games (QRM-SG), to learn the best-response strategy at Nash equilibrium for each agent. In QRM-SG, we define the Q-function at a Nash equilibrium in augmented state space. The augmented state space integrates the state of the stochastic game and the state of reward machines. Each agent learns the Q-functions of all agents in the system. We prove that Q-functions learned in QRM-SG converge to the Q-functions at a Nash equilibrium if the stage game at each time step during learning has a global optimum point or a saddle point, and the agents update Q-functions based on the best-response strategy at this point. We use the Lemke-Howson method to derive the best-response strategy given current Q-functions. The three case studies show that QRM-SG can learn the best-response strategies effectively. QRM-SG learns the best-response strategies after around 7500 episodes in Case Study I, 1000 episodes in Case Study II, and 1500 episodes in Case Study III, while baseline methods such as Nash Q-learning and MADDPG fail to converge to the Nash equilibrium in all three case studies.

We investigate an infinite-horizon average reward Markov Decision Process (MDP) with delayed, composite, and partially anonymous reward feedback. The delay and compositeness of rewards mean that rewards generated as a result of taking an action at a given state are fragmented into different components, and they are sequentially realized at delayed time instances. The partial anonymity attribute implies that a learner, for each state, only observes the aggregate of past reward components generated as a result of different actions taken at that state, but realized at the observation instance. We propose an algorithm named $\mathrm{DUCRL2}$ to obtain a near-optimal policy for this setting and show that it achieves a regret bound of $\tilde{\mathcal{O}}\left(DS\sqrt{AT} + d (SA)^3\right)$ where $S$ and $A$ are the sizes of the state and action spaces, respectively, $D$ is the diameter of the MDP, $d$ is a parameter upper bounded by the maximum reward delay, and $T$ denotes the time horizon. This demonstrates the optimality of the bound in the order of $T$, and an additive impact of the delay.