Recently it has been shown that tensor networks (TNs) have the ability to represent the expected return of a single-agent finite Markov decision process (FMDP). The TN represents a distribution model, where all possible trajectories are considered. When extending these ideas to a multi-agent setting, distribution models suffer from the curse of dimensionality: the exponential relation between the number of possible trajectories and the number of agents. The key advantage of using TNs in this setting is that there exists a large number of established optimisation and decomposition techniques that are specific to TNs, that one can apply to ensure the most efficient representation is found. In this report, these methods are used to form a TN that represents the expected return of a multi-agent reinforcement learning (MARL) task. This model is then applied to a 2 agent random walker example, where it was shown that the policy is correctly optimised using a DMRG technique. Finally, I demonstrate the use of an exact decomposition technique, reducing the number of elements in the tensors by 97.5%, without experiencing any loss of information.

Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of interest, however, it is possible to observe the behavior of multiple experts with different degree of optimality (e.g., racing drivers whose skills ranges from amateurs to professionals). For this reason, in this work, we extend the IRL formulation to problems where, in addition to demonstrations from the optimal agent, we can observe the behavior of multiple sub-optimal experts. Given this problem, we first study the theoretical properties of the class of reward functions that are compatible with a given set of experts, i.e., the feasible reward set. Our results show that the presence of multiple sub-optimal experts can significantly shrink the set of compatible rewards. Furthermore, we study the statistical complexity of estimating the feasible reward set with a generative model. To this end, we analyze a uniform sampling algorithm that results in being minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to the one of the optimal agent.

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model based algorithm to optimize preference learning, which first fitting a reward model for preference score, and then optimizing generating policy with on-policy PPO algorithm to maximize the reward. The processing of RLHF is complex, time-consuming and unstable. Direct Preference Optimization (DPO) algorithm using off-policy algorithm to direct optimize generating policy and eliminating the need for reward model, which is data efficient and stable. DPO use Bradley-Terry model and log-loss which leads to over-fitting to the preference data at the expense of ignoring KL-regularization term when preference is deterministic. IPO uses a root-finding MSE loss to solve the ignoring KL-regularization problem. In this paper, we'll figure out, although IPO fix the problem when preference is deterministic, but both DPO and IPO fails the KL-regularization term because the support of preference distribution not equal to reference distribution. Then, we design a simple and intuitive off-policy preference optimization algorithm from an importance sampling view, which we call Maximum Preference Optimization (MPO), and add off-policy KL-regularization terms which makes KL-regularization truly effective. The objective of MPO bears resemblance to RLHF's objective, and likes IPO, MPO is off-policy. So, MPO attains the best of both worlds. To simplify the learning process and save memory usage, MPO eliminates the needs for both reward model and reference policy.

We present a new fab-in-the-loop reinforcement learning algorithm for the design of nano-photonic components that accounts for the imperfections present in nanofabrication processes. As a demonstration of the potential of this technique, we apply it to the design of photonic crystal grating couplers fabricated on an air clad 220 nm silicon on insulator single etch platform. This fab-in-the-loop algorithm improves the insertion loss from 8.8 to 3.24 dB. The widest bandwidth designs produced using our fab-in-the-loop algorithm can cover a 150 nm bandwidth with less than 10.2 dB of loss at their lowest point.

In two-time-scale stochastic approximation (SA), two iterates are updated at varying speeds using different step sizes, with each update influencing the other. Previous studies in linear two-time-scale SA have found that the convergence rates of the mean-square errors for these updates are dependent solely on their respective step sizes, leading to what is referred to as decoupled convergence. However, the possibility of achieving this decoupled convergence in nonlinear SA remains less understood. Our research explores the potential for finite-time decoupled convergence in nonlinear two-time-scale SA. We find that under a weaker Lipschitz condition, traditional analyses are insufficient for achieving decoupled convergence. This finding is further numerically supported by a counterexample. But by introducing an additional condition of nested local linearity, we show that decoupled convergence is still feasible, contingent on the appropriate choice of step sizes associated with smoothness parameters. Our analysis depends on a refined characterization of the matrix cross term between the two iterates and utilizes fourth-order moments to control higher-order approximation errors induced by the local linearity assumption.

Deep reinforcement learning (DRL) methods have recently shown promise in path planning tasks. However, when dealing with global planning tasks, these methods face serious challenges such as poor convergence and generalization. To this end, we propose an attention-enhanced DRL method called LOPA (Learn Once Plan Arbitrarily) in this paper. Firstly, we analyze the reasons of these problems from the perspective of DRL's observation, revealing that the traditional design causes DRL to be interfered by irrelevant map information. Secondly, we develop the LOPA which utilizes a novel attention-enhanced mechanism to attain an improved attention capability towards the key information of the observation. Such a mechanism is realized by two steps: (1) an attention model is built to transform the DRL's observation into two dynamic views: local and global, significantly guiding the LOPA to focus on the key information on the given maps; (2) a dual-channel network is constructed to process these two views and integrate them to attain an improved reasoning capability. The LOPA is validated via multi-objective global path planning experiments. The result suggests the LOPA has improved convergence and generalization performance as well as great path planning efficiency.

Decision-making stands as a pivotal component in the realm of autonomous vehicles (AVs), playing a crucial role in navigating the intricacies of autonomous driving. Amidst the evolving landscape of data-driven methodologies, enhancing decision-making performance in complex scenarios has emerged as a prominent research focus. Despite considerable advancements, current learning-based decision-making approaches exhibit potential for refinement, particularly in aspects of policy articulation and safety assurance. To address these challenges, we introduce DDM-Lag, a Diffusion Decision Model,augmented with Lagrangian-based safety enhancements.In our approach, the autonomous driving decision-making conundrum is conceptualized as a Constrained Markov Decision Process (CMDP). We have crafted an Actor-Critic framework, wherein the diffusion model is employed as the actor,facilitating policy exploration and learning. The integration of safety constraints in the CMDP and the adoption of a Lagrangian relaxation-based policy optimization technique ensure enhanced decision safety. A PID controller is employed for the stable updating of model parameters. The effectiveness of DDM-Lag is evaluated through different driving tasks, showcasing improvements in decision-making safety and overall performance compared to baselines.

As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively evaluate algorithms that tackle the ``open-world''. To this end, we introduce NovelGym, a flexible and adaptable ecosystem designed to simulate gridworld environments, serving as a robust platform for benchmarking reinforcement learning (RL) and hybrid planning and learning agents in open-world contexts. The modular architecture of NovelGym facilitates rapid creation and modification of task environments, including multi-agent scenarios, with multiple environment transformations, thus providing a dynamic testbed for researchers to develop open-world AI agents.

Addressing this, we introduce ClusterComm, a fully decentralized MARL framework where agents communicate discretely without a central control unit. ClusterComm utilizes Mini-Batch-K-Means clustering on the last hidden layer's activations of an agent's policy network, translating them into discrete messages. This approach outperforms no communication and competes favorably with unbounded, continuous communication and hence poses a simple yet effective strategy for enhancing collaborative task-solving in MARL.

The emergence of on-demand ride pooling services allows each vehicle to serve multiple passengers at a time, thus increasing drivers' income and enabling passengers to travel at lower prices than taxi/car on-demand services (only one passenger can be assigned to a car at a time like UberX and Lyft). Although on-demand ride pooling services can bring so many benefits, ride pooling services need a well-defined matching strategy to maximize the benefits for all parties (passengers, drivers, aggregation companies and environment), in which the regional dispatching of vehicles has a significant impact on the matching and revenue. Existing algorithms often only consider revenue maximization, which makes it difficult for requests with unusual distribution to get a ride. How to increase revenue while ensuring a reasonable assignment of requests brings a challenge to ride pooling service companies (aggregation companies). In this paper, we propose a framework for vehicle dispatching for ride pooling tasks, which splits the city into discrete dispatching regions and uses the reinforcement learning (RL) algorithm to dispatch vehicles in these regions. We also consider the mutual information (MI) between vehicle and order distribution as the intrinsic reward of the RL algorithm to improve the correlation between their distributions, thus ensuring the possibility of getting a ride for unusually distributed requests. In experimental results on a real-world taxi dataset, we demonstrate that our framework can significantly increase revenue up to an average of 3\% over the existing best on-demand ride pooling method.