Supervised learning is often computationally easy in practice. But to what extent does this mean that other modes of learning, such as reinforcement learning (RL), ought to be computationally easy by extension? In this work we show the first cryptographic separation between RL and supervised learning, by exhibiting a class of block MDPs and associated decoding functions where reward-free exploration is provably computationally harder than the associated regression problem. We also show that there is no computationally efficient algorithm for reward-directed RL in block MDPs, even when given access to an oracle for this regression problem. It is known that being able to perform regression in block MDPs is necessary for finding a good policy; our results suggest that it is not sufficient. Our separation lower bound uses a new robustness property of the Learning Parities with Noise (LPN) hardness assumption, which is crucial in handling the dependent nature of RL data. We argue that separations and oracle lower bounds, such as ours, are a more meaningful way to prove hardness of learning because the constructions better reflect the practical reality that supervised learning by itself is often not the computational bottleneck.

We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment in which coordination is central. In LLE, agents depend on each other to make progress (interdependence), must jointly take specific sequences of actions to succeed (perfect coordination), and accomplishing those joint actions does not yield any intermediate reward (zero-incentive dynamics). The challenge of such problems lies in the difficulty of escaping state space bottlenecks caused by interdependence steps since escaping those bottlenecks is not rewarded. We test multiple state-of-the-art value-based MARL algorithms against LLE and show that they consistently fail at the collaborative task because of their inability to escape state space bottlenecks, even though they successfully achieve perfect coordination. We show that Q-learning extensions such as prioritised experience replay and n-steps return hinder exploration in environments with zero-incentive dynamics, and find that intrinsic curiosity with random network distillation is not sufficient to escape those bottlenecks. We demonstrate the need for novel methods to solve this problem and the relevance of LLE as cooperative MARL benchmark.

In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation. Previous methods have generally solved this problem by domain alignment, which incurs extra computation and storage costs, and these methods fail to handle the \textit{hard cases} where the viewpoint gap is too large. To alleviate the above problems, we introduce active sensoring in the visual IL setting and propose a model-based SENSory imitatOR (SENSOR) to automatically change the agent's perspective to match the expert's. SENSOR jointly learns a world model to capture the dynamics of latent states, a sensor policy to control the camera, and a motor policy to control the agent. Experiments on visual locomotion tasks show that SENSOR can efficiently simulate the expert's perspective and strategy, and outperforms most baseline methods.

The novel Internet of Things (IoT) paradigm is composed of a growing number of heterogeneous smart objects and services that are transforming architectures and applications, increasing systems' complexity, and the need for reliability and autonomy. In this context, both smart objects and services are often provided by third parties which do not give full transparency regarding the security and privacy of the features offered. Although machine-based Service Level Agreements (SLA) have been recently leveraged to establish and share policies in Cloud-based scenarios, and also in the IoT context, the issue of making end users aware of the overall system security levels and the fulfillment of their privacy requirements through the provision of the requested service remains a challenging task. To tackle this problem, we propose a complete framework that defines suitable levels of privacy and security requirements in the acquisition of services in IoT, according to the user needs. Through the use of a Reinforcement Learning based solution, a user agent, inside the environment, is trained to choose the best smart objects granting access to the target services. Moreover, the solution is designed to guarantee deadline requirements and user security and privacy needs. Finally, to evaluate the correctness and the performance of the proposed approach we illustrate an extensive experimental analysis.

To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during training, we posit that considering a range of edge-case trajectories provides a more comprehensive understanding of their inherent behavior. To induce such scenarios, we introduce a disturbance to the initial state, optimizing it through an evolutionary algorithm to generate a diverse population of demonstrations. To evaluate the fitness of trajectories, REACT incorporates a joint fitness function that encourages both local and global diversity in the encountered states and chosen actions. Through assessments with policies trained for varying durations in discrete and continuous environments, we demonstrate the descriptive power of REACT. Our results highlight its effectiveness in revealing nuanced aspects of RL models' behavior beyond optimal performance, thereby contributing to improved interpretability.

Urban air mobility is an innovative mode of transportation in which electric vertical takeoff and landing (eVTOL) vehicles operate between nodes called vertiports. We outline a self-organized vertiport arrival system based on deep reinforcement learning. The airspace around the vertiport is assumed to be circular, and the vehicles can freely operate inside. Each aircraft is considered an individual agent and follows a shared policy, resulting in decentralized actions that are based on local information. We investigate the development of the reinforcement learning policy during training and illustrate how the algorithm moves from suboptimal local holding patterns to a safe and efficient final policy. The latter is validated in simulation-based scenarios and also deployed on small-scale unmanned aerial vehicles to showcase its real-world usability.

We address the challenge of sampling and remote estimation for autoregressive Markovian processes in a multi-hop wireless network with statistically-identical agents. Agents cache the most recent samples from others and communicate over wireless collision channels governed by an underlying graph topology. Our goal is to minimize time-average estimation error and/or age of information with decentralized scalable sampling and transmission policies, considering both oblivious (where decision-making is independent of the physical processes) and non-oblivious policies (where decision-making depends on physical processes). We prove that in oblivious policies, minimizing estimation error is equivalent to minimizing the age of information. The complexity of the problem, especially the multi-dimensional action spaces and arbitrary network topologies, makes theoretical methods for finding optimal transmission policies intractable. We optimize the policies using a graphical multi-agent reinforcement learning framework, where each agent employs a permutation-equivariant graph neural network architecture. Theoretically, we prove that our proposed framework exhibits desirable transferability properties, allowing transmission policies trained on small- or moderate-size networks to be executed effectively on large-scale topologies. Numerical experiments demonstrate that (i) Our proposed framework outperforms state-of-the-art baselines; (ii) The trained policies are transferable to larger networks, and their performance gains increase with the number of agents; (iii) The training procedure withstands non-stationarity even if we utilize independent learning techniques; and, (iv) Recurrence is pivotal in both independent learning and centralized training and decentralized execution, and improves the resilience to non-stationarity in independent learning.

Cooperative intelligent transport systems rely on a set of Vehicle-to-Everything (V2X) applications to enhance road safety. Emerging new V2X applications like Advanced Driver Assistance Systems (ADASs) and Connected Autonomous Driving (CAD) applications depend on a significant amount of shared data and require high reliability, low end-to-end (E2E) latency, and high throughput. However, present V2X communication technologies such as ITS-G5 and C-V2X (Cellular V2X) cannot satisfy these requirements alone. In this paper, we propose an intelligent, scalable hybrid vehicular communication architecture that leverages the performance of multiple Radio Access Technologies (RATs) to meet the needs of these applications. Then, we propose a communication mode selection algorithm based on Deep Reinforcement Learning (DRL) to maximize the network's reliability while limiting resource consumption. Finally, we assess our work using the platooning scenario that requires high reliability. Numerical results reveal that the hybrid vehicular communication architecture has the potential to enhance the packet reception rate (PRR) by up to 30% compared to both the static RAT selection strategy and the multi-criteria decision-making (MCDM) selection algorithm. Additionally, it improves the efficiency of the redundant communication mode by 20% regarding resource consumption

Offline reinforcement learning learns from a static dataset without interacting with the environment, which ensures security and thus owns a good prospect of application. However, directly applying naive reinforcement learning methods usually fails in an offline environment due to function approximation errors caused by out-of-distribution(OOD) actions. To solve this problem, existing algorithms mainly penalize the Q-value of OOD actions, the quality of whose constraints also matter. Imprecise constraints may lead to suboptimal solutions, while precise constraints require significant computational costs. In this paper, we propose a novel count-based method for continuous domains, called Grid-Mapping Pseudo-Count method(GPC), to penalize the Q-value appropriately and reduce the computational cost. The proposed method maps the state and action space to discrete space and constrains their Q-values through the pseudo-count. It is theoretically proved that only a few conditions are needed to obtain accurate uncertainty constraints in the proposed method. Moreover, we develop a Grid-Mapping Pseudo-Count Soft Actor-Critic(GPC-SAC) algorithm using GPC under the Soft Actor-Critic(SAC) framework to demonstrate the effectiveness of GPC. The experimental results on D4RL benchmark datasets show that GPC-SAC has better performance and less computational cost compared to other algorithms.

Mechanical ventilation is a critical life-support intervention that uses a machine to deliver controlled air and oxygen to a patient's lungs, assisting or replacing spontaneous breathing. While several data-driven approaches have been proposed to optimize ventilator control strategies, they often lack interpretability and agreement with general domain knowledge. This paper proposes a methodology for interpretable reinforcement learning (RL) using decision trees for mechanical ventilation control. Using a causal, nonparametric model-based off-policy evaluation, we evaluate the policies in their ability to gain increases in SpO2 while avoiding aggressive ventilator settings which are known to cause ventilator induced lung injuries and other complications. Numerical experiments using MIMIC-III data on the stays of real patients' intensive care unit stays demonstrate that the decision tree policy outperforms the behavior cloning policy and is comparable to state-of-the-art RL policy. Future work concerns better aligning the cost function with medical objectives to generate deeper clinical insights.