When solving long-horizon tasks, it is intriguing to decompose the high-level task into subtasks. Decomposing experiences into reusable subtasks can improve data efficiency, accelerate policy generalization, and in general provide promising solutions to multi-task reinforcement learning and imitation learning problems. However, the concept of subtasks is not sufficiently understood and modeled yet, and existing works often overlook the true structure of the data generation process: subtasks are the results of a selection mechanism on actions, rather than possible underlying confounders or intermediates. Specifically, we provide a theory to identify, and experiments to verify the existence of selection variables in such data. These selections serve as subgoals that indicate subtasks and guide policy. In light of this idea, we develop a sequential non-negative matrix factorization (seq-NMF) method to learn these subgoals and extract meaningful behavior patterns as subtasks. Our empirical results on a challenging Kitchen environment demonstrate that the learned subtasks effectively enhance the generalization to new tasks in multi-task imitation learning scenarios. The codes are provided at this link.

Traditionally, model-based reinforcement learning (MBRL) methods exploit neural networks as flexible function approximators to represent $\textit{a priori}$ unknown environment dynamics. However, training data are typically scarce in practice, and these black-box models often fail to generalize. Modeling architectures that leverage known physics can substantially reduce the complexity of system-identification, but break down in the face of complex phenomena such as contact. We introduce a novel framework for learning semi-structured dynamics models for contact-rich systems which seamlessly integrates structured first principles modeling techniques with black-box auto-regressive models. Specifically, we develop an ensemble of probabilistic models to estimate external forces, conditioned on historical observations and actions, and integrate these predictions using known Lagrangian dynamics. With this semi-structured approach, we can make accurate long-horizon predictions with substantially less data than prior methods. We leverage this capability and propose Semi-Structured Reinforcement Learning ($\texttt{SSRL}$) a simple model-based learning framework which pushes the sample complexity boundary for real-world learning. We validate our approach on a real-world Unitree Go1 quadruped robot, learning dynamic gaits -- from scratch -- on both hard and soft surfaces with just a few minutes of real-world data. Video and code are available at: https://sites.google.com/utexas.edu/ssrl

Reinforcement learning problems often involve large action spaces arising from the simultaneous execution of multiple sub-actions, resulting in combinatorial action spaces. Learning in combinatorial action spaces is difficult due to the exponential growth in action space size with the number of sub-actions and the dependencies among these sub-actions. In offline settings, this challenge is compounded by limited and suboptimal data. Current methods for offline learning in combinatorial spaces simplify the problem by assuming sub-action independence. We propose Branch Value Estimation (BVE), which effectively captures sub-action dependencies and scales to large combinatorial spaces by learning to evaluate only a small subset of actions at each timestep. Our experiments show that BVE outperforms state-of-the-art methods across a range of action space sizes.

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others' behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework allows agents to conduct legible actions so as to help others optimise their behaviors. In addition, we design a series of problem domains that emulate a common scenario and best characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and costs less training time compared to several multiagent reinforcement learning algorithms.

Many reinforcement learning (RL) algorithms are too costly to use in practice due to the large sizes $S, A$ of the problem's state and action space. To resolve this issue, we study transfer RL with latent low rank structure. We consider the problem of transferring a latent low rank representation when the source and target MDPs have transition kernels with Tucker rank $(S , d, A )$, $(S , S , d), (d, S, A )$, or $(d , d , d )$. In each setting, we introduce the transfer-ability coefficient $\alpha$ that measures the difficulty of representational transfer. Our algorithm learns latent representations in each source MDP and then exploits the linear structure to remove the dependence on $S, A $, or $S A$ in the target MDP regret bound. We complement our positive results with information theoretic lower bounds that show our algorithms (excluding the ($d, d, d$) setting) are minimax-optimal with respect to $\alpha$.

Many practical applications of online reinforcement learning require the satisfaction of safety constraints while learning about the unknown environment. In this work, we study Linear Quadratic Regulator (LQR) learning with unknown dynamics, but with the additional constraint that the position must stay within a safe region for the entire trajectory with high probability. Unlike in previous works, we allow for both bounded and unbounded noise distributions and study stronger baselines of nonlinear controllers that are better suited for constrained problems than linear controllers. Due to these complications, we focus on 1-dimensional state- and action- spaces, however we also discuss how we expect the high-level takeaways can generalize to higher dimensions. Our primary contribution is the first $\tilde{O}_T(\sqrt{T})$-regret bound for constrained LQR learning, which we show relative to a specific baseline of non-linear controllers. We then prove that, for any non-linear baseline satisfying natural assumptions, $\tilde{O}_T(\sqrt{T})$-regret is possible when the noise distribution has sufficiently large support and $\tilde{O}_T(T^{2/3})$-regret is possible for any subgaussian noise distribution. An overarching theme of our results is that enforcing safety provides "free exploration" that compensates for the added cost of uncertainty in safety constrained control, resulting in the same regret rate as in the unconstrained problem.

Low-Earth orbit (LEO) satellites utilizing beam hopping (BH) technology offer extensive coverage, low latency, high bandwidth, and significant flexibility. However, the uneven geographical distribution and temporal variability of ground traffic demands, combined with the high mobility of LEO satellites, present significant challenges for efficient beam resource utilization. Traditional BH methods based on GEO satellites fail to address issues such as satellite interference, overlapping coverage, and mobility. This paper explores a Digital Twin (DT)-based collaborative resource allocation network for multiple LEO satellites with overlapping coverage areas. A two-tier optimization problem, focusing on load balancing and cell service fairness, is proposed to maximize throughput and minimize inter-cell service delay. The DT layer optimizes the allocation of overlapping coverage cells by designing BH patterns for each satellite, while the LEO layer optimizes power allocation for each selected service cell. At the DT layer, an Actor-Critic network is deployed on each agent, with a global critic network in the cloud center. The A3C algorithm is employed to optimize the DT layer. Concurrently, the LEO layer optimization is performed using a Multi-Agent Reinforcement Learning algorithm, where each beam functions as an independent agent. The simulation results show that this method reduces satellite load disparity by about 72.5% and decreases the average delay to 12ms. Additionally, our approach outperforms other benchmarks in terms of throughput, ensuring a better alignment between offered and requested data.

Quantum machine learning leverages quantum computing to enhance accuracy and reduce model complexity compared to classical approaches, promising significant advancements in various fields. Within this domain, quantum reinforcement learning has garnered attention, often realized using variational quantum circuits to approximate the policy function. This paper addresses the robustness and generalization of quantum reinforcement learning by combining principles from quantum computing and control theory. Leveraging recent results on robust quantum machine learning, we utilize Lipschitz bounds to propose a regularized version of a quantum policy gradient approach, named the RegQPG algorithm. We show that training with RegQPG improves the robustness and generalization of the resulting policies. Furthermore, we introduce an algorithmic variant that incorporates curriculum learning, which minimizes failures during training. Our findings are validated through numerical experiments, demonstrating the practical benefits of our approach.

The development of sophisticated models for video-to-video synthesis has been facilitated by recent advances in deep reinforcement learning and generative adversarial networks (GANs). In this paper, we propose RL-V2V-GAN, a new deep neural network approach based on reinforcement learning for unsupervised conditional video-to-video synthesis. While preserving the unique style of the source video domain, our approach aims to learn a mapping from a source video domain to a target video domain. We train the model using policy gradient and employ ConvLSTM layers to capture the spatial and temporal information by designing a fine-grained GAN architecture and incorporating spatio-temporal adversarial goals. The adversarial losses aid in content translation while preserving style. Unlike traditional video-to-video synthesis methods requiring paired inputs, our proposed approach is more general because it does not require paired inputs. Thus, when dealing with limited videos in the target domain, i.e., few-shot learning, it is particularly effective. Our experiments show that RL-V2V-GAN can produce temporally coherent video results. These results highlight the potential of our approach for further advances in video-to-video synthesis.

Traditional economic models often rely on fixed assumptions about market dynamics, limiting their ability to capture the complexities and stochastic nature of real-world scenarios. However, reality is more complex and includes noise, making traditional models assumptions not met in the market. In this paper, we explore the application of deep reinforcement learning (DRL) to obtain optimal production strategies in microeconomic market environments to overcome the limitations of traditional models. Concretely, we propose a DRL-based approach to obtain an effective policy in competitive markets with multiple producers, each optimizing their production decisions in response to fluctuating demand, supply, prices, subsidies, fixed costs, total production curve, elasticities and other effects contaminated by noise. Our framework enables agents to learn adaptive production policies to several simulations that consistently outperform static and random strategies. As the deep neural networks used by the agents are universal approximators of functions, DRL algorithms can represent in the network complex patterns of data learnt by trial and error that explain the market. Through extensive simulations, we demonstrate how DRL can capture the intricate interplay between production costs, market prices, and competitor behavior, providing insights into optimal decision-making in dynamic economic settings. The results show that agents trained with DRL can strategically adjust production levels to maximize long-term profitability, even in the face of volatile market conditions. We believe that the study bridges the gap between theoretical economic modeling and practical market simulation, illustrating the potential of DRL to revolutionize decision-making in market strategies.