Deep Reinforcement Learning (DRL) policies are critically vulnerable to adversarial noise in observations, posing severe risks in safety-critical scenarios. For example, a self-driving car receiving manipulated sensory inputs about traffic signs could lead to catastrophic outcomes. Existing strategies to fortify RL algorithms against such adversarial perturbations generally fall into two categories: (a) using regularization methods that enhance robustness by incorporating adversarial loss terms into the value objectives, and (b) adopting "maximin" principles, which focus on maximizing the minimum value to ensure robustness. While regularization methods reduce the likelihood of successful attacks, their effectiveness drops significantly if an attack does succeed. On the other hand, maximin objectives, although robust, tend to be overly conservative. To address this challenge, we introduce a novel objective called Adversarial Counterfactual Error (ACoE), which naturally balances optimizing value and robustness against adversarial attacks. To optimize ACoE in a scalable manner in model-free settings, we propose a theoretically justified surrogate objective known as Cumulative-ACoE (C-ACoE). The core idea of optimizing C-ACoE is utilizing the belief about the underlying true state given the adversarially perturbed observation. Our empirical evaluations demonstrate that our method outperforms current state-of-the-art approaches for addressing adversarial RL problems across all established benchmarks (MuJoCo, Atari, and Highway) used in the literature.

This work introduces a novel value decomposition algorithm, termed \textit{Dynamic Deep Factor Graphs} (DDFG). Unlike traditional coordination graphs, DDFG leverages factor graphs to articulate the decomposition of value functions, offering enhanced flexibility and adaptability to complex value function structures. Central to DDFG is a graph structure generation policy that innovatively generates factor graph structures on-the-fly, effectively addressing the dynamic collaboration requirements among agents. DDFG strikes an optimal balance between the computational overhead associated with aggregating value functions and the performance degradation inherent in their complete decomposition. Through the application of the max-sum algorithm, DDFG efficiently identifies optimal policies. We empirically validate DDFG's efficacy in complex scenarios, including higher-order predator-prey tasks and the StarCraft II Multi-agent Challenge (SMAC), thus underscoring its capability to surmount the limitations faced by existing value decomposition algorithms. DDFG emerges as a robust solution for MARL challenges that demand nuanced understanding and facilitation of dynamic agent collaboration. The implementation of DDFG is made publicly accessible, with the source code available at \url{https://github.com/SICC-Group/DDFG}.

The emerging field of \emph{value awareness engineering} claims that software agents and systems should be value-aware, i.e. they must make decisions in accordance with human values. In this context, such agents must be capable of explicitly reasoning as to how far different courses of action are aligned with these values. For this purpose, values are often modelled as preferences over states or actions, which are then aggregated to determine the sequences of actions that are maximally aligned with a certain value. Recently, additional value admissibility constraints at this level have been considered as well. However, often relaxed versions of these constraints are needed, and this increases considerably the complexity of computing value-aligned policies. To obtain efficient algorithms that make value-aligned decisions considering admissibility relaxation, we propose the use of learning techniques, in particular, we have used constrained reinforcement learning algorithms. In this paper, we present two algorithms, $\epsilon\text{-}ADQL$ for strategies based on local alignment and its extension $\epsilon\text{-}CADQL$ for a sequence of decisions. We have validated their efficiency in a water distribution problem in a drought scenario.

Today's distributed and pervasive computing addresses large-scale cyber-physical ecosystems, characterised by dense and large networks of devices capable of computation, communication and interaction with the environment and people. While most research focusses on treating these systems as "composites" (i.e., heterogeneous functional complexes), recent developments in fields such as self-organising systems and swarm robotics have opened up a complementary perspective: treating systems as "collectives" (i.e., uniform, collaborative, and self-organising groups of entities). This article explores the motivations, state of the art, and implications of this "collective computing paradigm" in software engineering, discusses its peculiar challenges, and outlines a path for future research, touching on aspects such as macroprogramming, collective intelligence, self-adaptive middleware, learning, synthesis, and experimentation of collective behaviour.

Robotic systems driven by artificial muscles present unique challenges due to the nonlinear dynamics of actuators and the complex designs of mechanical structures. Traditional model-based controllers often struggle to achieve desired control performance in such systems. Deep reinforcement learning (DRL), a trending machine learning technique widely adopted in robot control, offers a promising alternative. However, integrating DRL into these robotic systems faces significant challenges, including the requirement for large amounts of training data and the inevitable sim-to-real gap when deployed to real-world robots. This paper proposes an efficient reinforcement learning control framework with sim-to-real transfer to address these challenges. Bootstrap and augmentation enhancements are designed to improve the data efficiency of baseline DRL algorithms, while a sim-to-real transfer technique, namely randomization of muscle dynamics, is adopted to bridge the gap between simulation and real-world deployment. Extensive experiments and ablation studies are conducted utilizing two string-type artificial muscle-driven robotic systems including a two degree-of-freedom robotic eye and a parallel robotic wrist, the results of which demonstrate the effectiveness of the proposed learning control strategy.

Radio Resource Management is a challenging topic in future 6G networks where novel applications create strong competition among the users for the available resources. In this work we consider the frequency scheduling problem in a multi-user MIMO system. Frequency resources need to be assigned to a set of users while allowing for concurrent transmissions in the same sub-band. Traditional methods are insufficient to cope with all the involved constraints and uncertainties, whereas reinforcement learning can directly learn near-optimal solutions for such complex environments. However, the scheduling problem has an enormous action space accounting for all the combinations of users and sub-bands, so out-of-the-box algorithms cannot be used directly. In this work, we propose a scheduler based on action-branching over sub-bands, which is a deep Q-learning architecture with parallel decision capabilities. The sub-bands learn correlated but local decision policies and altogether they optimize a global reward. To improve the scaling of the architecture with the number of sub-bands, we propose variations (Unibranch, Graph Neural Network-based) that reduce the number of parameters to learn. The parallel decision making of the proposed architecture allows to meet short inference time requirements in real systems. Furthermore, the deep Q-learning approach permits online fine-tuning after deployment to bridge the sim-to-real gap. The proposed architectures are evaluated against relevant baselines from the literature showing competitive performance and possibilities of online adaptation to evolving environments.

The expected regret of any reinforcement learning algorithm is lower bounded by $\Omega\left(\sqrt{DXAT}\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the size of the action space and $T$ the number of time steps. However, this lower bound is general. A smaller regret can be obtained by taking into account some specific knowledge of the problem structure. In this article, we consider an admission control problem to an $M/M/c/S$ queue with $m$ job classes and class-dependent rewards and holding costs. Queuing systems often have a diameter that is exponential in the buffer size $S$, making the previous lower bound prohibitive for any practical use. We propose an algorithm inspired by UCRL2, and use the structure of the problem to upper bound the expected total regret by $O(S\log T + \sqrt{mT \log T})$ in the finite server case. In the infinite server case, we prove that the dependence of the regret on $S$ disappears.

\Ac{MPC} and \ac{RL} are two powerful control strategies with, arguably, complementary advantages. In this work, we show how actor-critic \ac{RL} techniques can be leveraged to improve the performance of \ac{MPC}. The \ac{RL} critic is used as an approximation of the optimal value function, and an actor roll-out provides an initial guess for primal variables of the \ac{MPC}. A parallel control architecture is proposed where each \ac{MPC} instance is solved twice for different initial guesses. Besides the actor roll-out initialization, a shifted initialization from the previous solution is used. Thereafter, the actor and the critic are again used to approximately evaluate the infinite horizon cost of these trajectories. The control actions from the lowest-cost trajectory are applied to the system at each time step. We establish that the proposed algorithm is guaranteed to outperform the original \ac{RL} policy plus an error term that depends on the accuracy of the critic and decays with the horizon length of the \ac{MPC} formulation. Moreover, we do not require globally optimal solutions for these guarantees to hold. The approach is demonstrated on an illustrative toy example and an \ac{AD} overtaking scenario.

This study considers the attack on reinforcement learning agents where the adversary aims to control the victim's behavior as specified by the adversary by adding adversarial modifications to the victim's state observation. While some attack methods reported success in manipulating the victim agent's behavior, these methods often rely on environment-specific heuristics. In addition, all existing attack methods require white-box access to the victim's policy. In this study, we propose a novel method for manipulating the victim agent in the black-box (i.e., the adversary is allowed to observe the victim's state and action only) and no-box (i.e., the adversary is allowed to observe the victim's state only) setting without requiring environment-specific heuristics. Our attack method is formulated as a bi-level optimization problem that is reduced to a distribution matching problem and can be solved by an existing imitation learning algorithm in the black-box and no-box settings. Empirical evaluations on several reinforcement learning benchmarks show that our proposed method has superior attack performance to baselines.

Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means of exploration, yet agents often struggle to handle novel situations, hindering generalization. To address these issues, we propose HackAtari, a framework introducing controlled novelty to the most common RL benchmark, the Atari Learning Environment. HackAtari allows us to create novel game scenarios (including simplification for curriculum learning), to swap the game elements' colors, as well as to introduce different reward signals for the agent. We demonstrate that current agents trained on the original environments include robustness failures, and evaluate HackAtari's efficacy in enhancing RL agents' robustness and aligning behavior through experiments using C51 and PPO. Overall, HackAtari can be used to improve the robustness of current and future RL algorithms, allowing Neuro-Symbolic RL, curriculum RL, causal RL, as well as LLM-driven RL. Our work underscores the significance of developing interpretable in RL agents.