We tackle in this paper an online network resource allocation problem with job transfers. The network is composed of many servers connected by communication links. The system operates in discrete time; at each time slot, the administrator reserves resources at servers for future job requests, and a cost is incurred for the reservations made. Then, after receptions, the jobs may be transferred between the servers to best accommodate the demands. This incurs an additional transport cost. Finally, if a job request cannot be satisfied, there is a violation that engenders a cost to pay for the blocked job. We propose a randomized online algorithm based on the exponentially weighted method. We prove that our algorithm enjoys a sub-linear in time regret, which indicates that the algorithm is adapting and learning from its experiences and is becoming more efficient in its decision-making as it accumulates more data. Moreover, we test the performance of our algorithm on artificial data and compare it against a reinforcement learning method where we show that our proposed method outperforms the latter.

The goal of programmatic Learning from Demonstration (LfD) is to learn a policy in a programming language that can be used to control a robot's behavior from a set of user demonstrations. This paper presents a new programmatic LfD algorithm that targets long-horizon robot tasks which require synthesizing programs with complex control flow structures, including nested loops with multiple conditionals. Our proposed method first learns a program sketch that captures the target program's control flow and then completes this sketch using an LLM-guided search procedure that incorporates a novel technique for proving unrealizability of programming-by-demonstration problems. We have implemented our approach in a new tool called PROLEX and present the results of a comprehensive experimental evaluation on 120 benchmarks involving complex tasks and environments. We show that, given a 120 second time limit, PROLEX can find a program consistent with the demonstrations in 80% of the cases. Furthermore, for 81% of the tasks for which a solution is returned, PROLEX is able to find the ground truth program with just one demonstration. In comparison, CVC5, a syntax guided synthesis tool, is only able to solve 25% of the cases even when given the ground truth program sketch, and an LLM-based approach, GPT-Synth, is unable to solve any of the tasks due to the environment complexity.

In the backdrop of an increasingly pressing need for effective urban and highway transportation systems, this work explores the synergy between model-based and learning-based strategies to enhance traffic flow management by use of an innovative approach to the problem of highway ramp metering control that embeds Reinforcement Learning techniques within the Model Predictive Control framework. The control problem is formulated as an RL task by crafting a suitable stage cost function that is representative of the traffic conditions, variability in the control action, and violations of a safety-critical constraint on the maximum number of vehicles in queue. An MPC-based RL approach, which merges the advantages of the two paradigms in order to overcome the shortcomings of each framework, is proposed to learn to efficiently control an on-ramp and to satisfy its constraints despite uncertainties in the system model and variable demands. Finally, simulations are performed on a benchmark from the literature consisting of a small-scale highway network. Results show that, starting from an MPC controller that has an imprecise model and is poorly tuned, the proposed methodology is able to effectively learn to improve the control policy such that congestion in the network is reduced and constraints are satisfied, yielding an improved performance compared to the initial controller.

Clinical diagnosis guidelines aim at specifying the steps that may lead to a diagnosis. Inspired by guidelines, we aim to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from electronic health records. We apply various deep reinforcement learning algorithms to this task and experiment on a synthetic but realistic dataset to differentially diagnose anemia and its subtypes and particularly evaluate the robustness of various approaches to noise and missing data. Experimental results show that the deep reinforcement learning algorithms show competitive performance compared to the state-of-the-art methods with the added advantage that they enable the progressive generation of a pathway to the suggested diagnosis, which can both guide and explain the decision process.

Policy gradient (PG) is widely used in reinforcement learning due to its scalability and good performance. In recent years, several variance-reduced PG methods have been proposed with a theoretical guarantee of converging to an approximate first-order stationary point (FOSP) with the sample complexity of $O(\epsilon^{-3})$. However, FOSPs could be bad local optima or saddle points. Moreover, these algorithms often use importance sampling (IS) weights which could impair the statistical effectiveness of variance reduction. In this paper, we propose a variance-reduced second-order method that uses second-order information in the form of Hessian vector products (HVP) and converges to an approximate second-order stationary point (SOSP) with sample complexity of $\tilde{O}(\epsilon^{-3})$. This rate improves the best-known sample complexity for achieving approximate SOSPs by a factor of $O(\epsilon^{-0.5})$. Moreover, the proposed variance reduction technique bypasses IS weights by using HVP terms. Our experimental results show that the proposed algorithm outperforms the state of the art and is more robust to changes in random seeds.

A significant bottleneck in applying current reinforcement learning algorithms to real-world scenarios is the need to reset the environment between every episode. This reset process demands substantial human intervention, making it difficult for the agent to learn continuously and autonomously. Several recent works have introduced autonomous reinforcement learning (ARL) algorithms that generate curricula for jointly training reset and forward policies. While their curricula can reduce the number of required manual resets by taking into account the agent's learning progress, they rely on task-specific knowledge, such as predefined initial states or reset reward functions. In this paper, we propose a novel ARL algorithm that can generate a curriculum adaptive to the agent's learning progress without task-specific knowledge. Our curriculum empowers the agent to autonomously reset to diverse and informative initial states. To achieve this, we introduce a success discriminator that estimates the success probability from each initial state when the agent follows the forward policy. The success discriminator is trained with relabeled transitions in a self-supervised manner. Our experimental results demonstrate that our ARL algorithm can generate an adaptive curriculum and enable the agent to efficiently bootstrap to solve sparse-reward maze navigation tasks, outperforming baselines with significantly fewer manual resets.

Robustness to noise is of utmost importance in reinforcement learning systems, particularly in military contexts where high stakes and uncertain environments prevail. Noise and uncertainty are inherent features of military operations, arising from factors such as incomplete information, adversarial actions, or unpredictable battlefield conditions. In RL, noise can critically impact decision-making, mission success, and the safety of personnel. Reward machines offer a powerful tool to express complex reward structures in RL tasks, enabling the design of tailored reinforcement signals that align with mission objectives. This paper considers the problem of the robustness of intelligence-driven reinforcement learning based on reward machines. The preliminary results presented suggest the need for further research in evidential reasoning and learning to harden current state-of-the-art reinforcement learning approaches before being mission-critical-ready.

In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settings. Despite their relevance, little to no attention has been directed to the study of their security implications and robustness to adversarial scenarios, likely due to their recent appearance in the literature. With my thesis, I aim to provide the first analysis of the security of RM-based reinforcement learning techniques, with the hope of motivating further research in the field, and I propose and evaluate a novel class of attacks on RM-based techniques: blinding attacks.

Offline reinforcement learning suffers from the out-of-distribution issue and extrapolation error. Most policy constraint methods regularize the density of the trained policy towards the behavior policy, which is too restrictive in most cases. We propose Supported Trust Region optimization (STR) which performs trust region policy optimization with the policy constrained within the support of the behavior policy, enjoying the less restrictive support constraint. We show that, when assuming no approximation and sampling error, STR guarantees strict policy improvement until convergence to the optimal support-constrained policy in the dataset. Further with both errors incorporated, STR still guarantees safe policy improvement for each step. Empirical results validate the theory of STR and demonstrate its state-of-the-art performance on MuJoCo locomotion domains and much more challenging AntMaze domains.

This paper aims to solve the contact-aware locomotion problem of a soft snake robot by developing bio-inspired contact-aware locomotion controllers. To provide effective contact information for the controllers, we develop a scale-covered sensor structure mimicking natural snakes' scale sensilla. In the design of the control framework, our core contribution is the development of a novel sensory feedback mechanism for the Matsuoka central pattern generator (CPG) network. This mechanism allows the Matsuoka CPG system to work like a "spinal cord" in the whole contact-aware control scheme, which simultaneously takes the stimuli including tonic input signals from the "brain" (a goal-tracking locomotion controller) and sensory feedback signals from the "reflex arc" (the contact reactive controller), and generates rhythmic signals to actuate the soft snake robot to slither through densely allocated obstacles. In the "reflex arc" design, we develop two distinctive types of reactive controllers -- 1) a reinforcement learning (RL) sensor regulator that learns to manipulate the sensory feedback inputs of the CPG system, and 2) a local reflexive sensor-CPG network that directly connects sensor readings and the CPG's feedback inputs in a specific topology. Combining with the locomotion controller and the Matsuoka CPG system, these two reactive controllers facilitate two different contact-aware locomotion control schemes. The two control schemes are tested and evaluated in both simulated and real soft snake robots, showing promising performance in the contact-aware locomotion tasks. The experimental results also validate the advantages of the modified Matsuoka CPG system with a new sensory feedback mechanism for bio-inspired robot controller design.