We consider discounted infinite horizon constrained Markov decision processes (CMDPs) where the goal is to find an optimal policy that maximizes the expected cumulative reward subject to expected cumulative constraints. Motivated by the application of CMDPs in online learning of safety-critical systems, we focus on developing an algorithm that ensures constraint satisfaction during learning. To this end, we develop a zeroth-order interior point approach based on the log barrier function of the CMDP. Under the commonly assumed conditions of Fisher non-degeneracy and bounded transfer error of the policy parameterization, we establish the theoretical properties of the algorithm. In particular, in contrast to existing CMDP approaches that ensure policy feasibility only upon convergence, our algorithm guarantees feasibility of the policies during the learning process and converges to the optimal policy with a sample complexity of $O(\varepsilon^{-6})$. In comparison to the state-of-the-art policy gradient-based algorithm, C-NPG-PDA, our algorithm requires an additional $O(\varepsilon^{-2})$ samples to ensure policy feasibility during learning with same Fisher-non-degenerate parameterization.

In this paper, we consider domain-adaptive imitation learning with visual observation, where an agent in a target domain learns to perform a task by observing expert demonstrations in a source domain. Domain adaptive imitation learning arises in practical scenarios where a robot, receiving visual sensory data, needs to mimic movements by visually observing other robots from different angles or observing robots of different shapes. To overcome the domain shift in cross-domain imitation learning with visual observation, we propose a novel framework for extracting domain-independent behavioral features from input observations that can be used to train the learner, based on dual feature extraction and image reconstruction. Empirical results demonstrate that our approach outperforms previous algorithms for imitation learning from visual observation with domain shift.

To keep as FFHQ dataset (image size 1024 1024). Nouveau VAE the Metaverse up-to-date, uplink data collection for object (NVAE) proposed by Vahdat et al. [10] further improved the modeling and updating are essential for VR applications. The performance of VAE and achieved satisfying results on various efficiency of data transmission has a direct impact on user high-quality image datasets. Li et al. [11] found that devices experience once there are demands to update the VR background, can select different scales of sub-models that requires less which is different from the traditional VR applications computational energy at the cost of reconstruction quality, and whose contents are not frequently updated. The 3-D modeling formulated the relationship between them. of remote area VR backgrounds including buildings (indoor and outdoor), roads, and natural environments are based on To cope with the challenge of wireless network coverage numerous photos taken on location, e.g., more than 1500 in remote areas, UAV-assisted data collection is considered as images with the average size of 10Mb are required to model a practical solution to set up flexible wireless networks for an area with historic buildings [?]. The data collection with heterogeneous user requirements [?], especially the research such large size poses requirements for both high transmission on UAV-enabled communication resource allocation, trajectory efficiency and wide network coverage.

In a standard view of the reinforcement learning problem, an agent's goal is to efficiently identify a policy that maximizes long-term reward. However, this perspective is based on a restricted view of learning as finding a solution, rather than treating learning as endless adaptation. In contrast, continual reinforcement learning refers to the setting in which the best agents never stop learning. Despite the importance of continual reinforcement learning, the community lacks a simple definition of the problem that highlights its commitments and makes its primary concepts precise and clear. To this end, this paper is dedicated to carefully defining the continual reinforcement learning problem. We formalize the notion of agents that "never stop learning" through a new mathematical language for analyzing and cataloging agents. Using this new language, we define a continual learning agent as one that can be understood as carrying out an implicit search process indefinitely, and continual reinforcement learning as the setting in which the best agents are all continual learning agents. We provide two motivating examples, illustrating that traditional views of multi-task reinforcement learning and continual supervised learning are special cases of our definition.

Intrinsically motivated exploration has proven useful for reinforcement learning, even without additional extrinsic rewards. When the environment is naturally represented as a graph, how to guide exploration best remains an open question. In this work, we propose a novel approach for exploring graph-structured data motivated by two theories of human curiosity: the information gap theory and the compression progress theory. The theories view curiosity as an intrinsic motivation to optimize for topological features of subgraphs induced by nodes visited in the environment. We use these proposed features as rewards for graph neural-network-based reinforcement learning. On multiple classes of synthetically generated graphs, we find that trained agents generalize to longer exploratory walks and larger environments than are seen during training. Our method computes more efficiently than the greedy evaluation of the relevant topological properties. The proposed intrinsic motivations bear particular relevance for recommender systems. We demonstrate that next-node recommendations considering curiosity are more predictive of human choices than PageRank centrality in several real-world graph environments.

Analysis of invasive sports such as soccer is challenging because the game situation changes continuously in time and space, and multiple agents individually recognize the game situation and make decisions. Previous studies using deep reinforcement learning have often considered teams as a single agent and valued the teams and players who hold the ball in each discrete event. Then it was challenging to value the actions of multiple players, including players far from the ball, in a spatiotemporally continuous state space. In this paper, we propose a method of valuing possible actions for on- and off-ball soccer players in a single holistic framework based on multi-agent deep reinforcement learning. We consider a discrete action space in a continuous state space that mimics that of Google research football and leverages supervised learning for actions in reinforcement learning. In the experiment, we analyzed the relationships with conventional indicators, season goals, and game ratings by experts, and showed the effectiveness of the proposed method. Our approach can assess how multiple players move continuously throughout the game, which is difficult to be discretized or labeled but vital for teamwork, scouting, and fan engagement.

Quantum computing holds great potential for advancing the limitations of machine learning algorithms to handle higher dimensions of data and reduce overall training parameters in deep learning (DL) models. This study uses a trainable variational quantum circuit (VQC) on a gate-based quantum computing model to investigate the potential for quantum benefit in a model-free reinforcement learning problem. Through a comprehensive investigation and evaluation of the current model and capabilities of quantum computers, we designed and trained a novel hybrid quantum neural network based on the latest Qiskit and PyTorch framework. We compared its performance with a full-classical CNN with and without an incorporated VQC. Our research provides insights into the potential of deep quantum learning to solve a maze problem and, potentially, other reinforcement learning problems. We conclude that reinforcement learning problems can be practical with reasonable training epochs. Moreover, a comparative study of full-classical and hybrid quantum neural networks is discussed to understand these two approaches' performance, advantages, and disadvantages to deep-Q learning problems, especially on larger-scale maze problems larger than 4x4.

Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models fall short by forcing a tradeoff between accuracy and interpretability. This tradeoff limits data-driven interpretations of human decision-making process. e.g. to audit medical decisions for biases and suboptimal practices, we require models of decision processes which provide concise descriptions of complex behaviors. Fundamentally, existing approaches are burdened by this tradeoff because they represent the underlying decision process as a universal policy, when in fact human decisions are dynamic and can change drastically with contextual information. Thus, we propose Contextualized Policy Recovery (CPR), which re-frames the problem of modeling complex decision processes as a multi-task learning problem in which complex decision policies are comprised of context-specific policies. CPR models each context-specific policy as a linear observation-to-action mapping, and generates new decision models $\textit{on-demand}$ as contexts are updated with new observations. CPR is compatible with fully offline and partially observable decision environments, and can be tailored to incorporate any recurrent black-box model or interpretable decision model. We assess CPR through studies on simulated and real data, achieving state-of-the-art performance on the canonical tasks of predicting antibiotic prescription in intensive care units ($+22\%$ AUROC vs. previous SOTA) and predicting MRI prescription for Alzheimer's patients ($+7.7\%$ AUROC vs. previous SOTA). With this improvement in predictive performance, CPR closes the accuracy gap between interpretable and black-box methods for policy learning, allowing high-resolution exploration and analysis of context-specific decision models.

Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences. Consequently, aligning these models with human ethics and preferences is an essential step toward ensuring their responsible and effective deployment in real-world applications. Prior research has primarily employed Reinforcement Learning from Human Feedback (RLHF) to address this problem, where generative models are fine-tuned with RL algorithms guided by a human-feedback-informed reward model. However, the inefficiencies and instabilities associated with RL algorithms frequently present substantial obstacles to the successful alignment, necessitating the development of a more robust and streamlined approach. To this end, we introduce a new framework, Reward rAnked FineTuning (RAFT), designed to align generative models effectively. Utilizing a reward model and a sufficient number of samples, our approach selects the high-quality samples, discarding those that exhibit undesired behavior, and subsequently enhancing the model by fine-tuning on these filtered samples. Our studies show that RAFT can effectively improve the model performance in both reward learning and other automated metrics in both large language models and diffusion models.

Humanitarian logistics operations face increasing difficulties due to rising demands for aid in disaster areas. This paper investigates the dynamic allocation of scarce relief supplies across multiple affected districts over time. It introduces a novel stochastic dynamic post-disaster inventory allocation problem with trucks and unmanned aerial vehicles delivering relief goods under uncertain supply and demand. The relevance of this humanitarian logistics problem lies in the importance of considering the inter-temporal social impact of deliveries. We achieve this by incorporating deprivation costs when allocating scarce supplies. Furthermore, we consider the inherent uncertainties of disaster areas and the potential use of cargo UAVs to enhance operational efficiency. This study proposes two anticipatory solution methods based on approximate dynamic programming, specifically decomposed linear value function approximation and neural network value function approximation to effectively manage uncertainties in the dynamic allocation process. We compare DL-VFA and NN-VFA with various state-of-the-art methods (exact re-optimization, PPO) and results show a 6-8% improvement compared to the best benchmarks. NN-VFA provides the best performance and captures nonlinearities in the problem, whereas DL-VFA shows excellent scalability against a minor performance loss. The experiments reveal that consideration of deprivation costs results in improved allocation of scarce supplies both across affected districts and over time. Finally, results show that deploying UAVs can play a crucial role in the allocation of relief goods, especially in the first stages after a disaster. The use of UAVs reduces transportation- and deprivation costs together by 16-20% and reduces maximum deprivation times by 19-40%, while maintaining similar levels of demand coverage, showcasing efficient and effective operations.