We study a subclass of $n$-player stochastic games, namely, stochastic games with independent chains and unknown transition matrices. In this class of games, players control their own internal Markov chains whose transitions do not depend on the states/actions of other players. However, players' decisions are coupled through their payoff functions. We assume players can receive only realizations of their payoffs, and that the players can not observe the states and actions of other players, nor do they know the transition probability matrices of their own Markov chain. Relying on a compact dual formulation of the game based on occupancy measures and the technique of confidence set to maintain high-probability estimates of the unknown transition matrices, we propose a fully decentralized mirror descent algorithm to learn an $\epsilon$-NE for this class of games. The proposed algorithm has the desired properties of independence, scalability, and convergence. Specifically, under no assumptions on the reward functions, we show the proposed algorithm converges in polynomial time in a weaker distance (namely, the averaged Nikaido-Isoda gap) to the set of $\epsilon$-NE policies with arbitrarily high probability. Moreover, assuming the existence of a variationally stable Nash equilibrium policy, we show that the proposed algorithm converges asymptotically to the stable $\epsilon$-NE policy with arbitrarily high probability. In addition to Markov potential games and linear-quadratic stochastic games, this work provides another subclass of $n$-player stochastic games that, under some mild assumptions, admit polynomial-time learning algorithms for finding their stationary $\epsilon$-NE policies.

Motivated by the need for a robust policy in the face of environment shifts between training and the deployment, we contribute to the theoretical foundation of distributionally robust reinforcement learning (DRRL). This is accomplished through a comprehensive modeling framework centered around distributionally robust Markov decision processes (DRMDPs). This framework obliges the decision maker to choose an optimal policy under the worst-case distributional shift orchestrated by an adversary. By unifying and extending existing formulations, we rigorously construct DRMDPs that embraces various modeling attributes for both the decision maker and the adversary. These attributes include adaptability granularity, exploring history-dependent, Markov, and Markov time-homogeneous decision maker and adversary dynamics. Additionally, we delve into the flexibility of shifts induced by the adversary, examining SA and S-rectangularity. Within this DRMDP framework, we investigate conditions for the existence or absence of the dynamic programming principle (DPP). From an algorithmic standpoint, the existence of DPP holds significant implications, as the vast majority of existing data and computationally efficiency RL algorithms are reliant on the DPP. To study its existence, we comprehensively examine combinations of controller and adversary attributes, providing streamlined proofs grounded in a unified methodology. We also offer counterexamples for settings in which a DPP with full generality is absent.

The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the CAP is a crucial step towards the successful deployment of RL in the real world since most decision problems provide feedback that is noisy, delayed, and with little or no information about the causes. These conditions make it hard to distinguish serendipitous outcomes from those caused by informed decision-making. However, the mathematical nature of credit and the CAP remains poorly understood and defined. In this survey, we review the state of the art of Temporal Credit Assignment (CA) in deep RL. We propose a unifying formalism for credit that enables equitable comparisons of state of the art algorithms and improves our understanding of the trade-offs between the various methods. We cast the CAP as the problem of learning the influence of an action over an outcome from a finite amount of experience. We discuss the challenges posed by delayed effects, transpositions, and a lack of action influence, and analyse how existing methods aim to address them. Finally, we survey the protocols to evaluate a credit assignment method, and suggest ways to diagnoses the sources of struggle for different credit assignment methods. Overall, this survey provides an overview of the field for new-entry practitioners and researchers, it offers a coherent perspective for scholars looking to expedite the starting stages of a new study on the CAP, and it suggests potential directions for future research

Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and has made progress in various fields. Specifically, cooperative MARL focuses on training a team of agents to cooperatively achieve tasks that are difficult for a single agent to handle. It has shown great potential in applications such as path planning, autonomous driving, active voltage control, and dynamic algorithm configuration. One of the research focuses in the field of cooperative MARL is how to improve the coordination efficiency of the system, while research work has mainly been conducted in simple, static, and closed environment settings. To promote the application of artificial intelligence in real-world, some research has begun to explore multi-agent coordination in open environments. These works have made progress in exploring and researching the environments where important factors might change. However, the mainstream work still lacks a comprehensive review of the research direction. In this paper, starting from the concept of reinforcement learning, we subsequently introduce multi-agent systems (MAS), cooperative MARL, typical methods, and test environments. Then, we summarize the research work of cooperative MARL from closed to open environments, extract multiple research directions, and introduce typical works. Finally, we summarize the strengths and weaknesses of the current research, and look forward to the future development direction and research problems in cooperative MARL in open environments.

In this paper, we propose a novel behavior planner that combines game theory with search-based planning for automated lane merging. Specifically, inspired by human drivers, we model the interaction between vehicles as a gap selection process. To overcome the challenge of multi-modal behavior exhibited by the surrounding vehicles, we formulate the trajectory selection as a matrix game and compute an equilibrium. Next, we validate our proposed planner in the high-fidelity simulator CARLA and demonstrate its effectiveness in handling interactions in dense traffic scenarios.

Markov chain Monte Carlo (MCMC) methods are simulated by local exploration of complex statistical distributions, and while bypassing the cumbersome requirement of a specific analytical expression for the target, this stochastic exploration of an uncertain parameter space comes at the expense of a large number of samples, and this computational complexity increases with parameter dimensionality. Although at the exploration level, some methods are proposed to accelerate the convergence of the algorithm, such as tempering, Hamiltonian Monte Carlo, Rao-redwellization, and scalable methods for better performance, it cannot avoid the stochastic nature of this exploration. We consider the target distribution as a mapping where the infinite-dimensional Eulerian space of the parameters consists of a number of deterministic submanifolds and propose a generalized energy metric, termed weighted Riesz energy, where a number of points is generated through pairwise interactions, to discretize rectifiable submanifolds. We study the properties of the point, called Riesz particle, and embed it into sequential MCMC, and we find that there will be higher acceptance rates with fewer evaluations, we validate it through experimental comparative analysis from a linear Gaussian state-space model with synthetic data and a non-linear stochastic volatility model with real-world data.

Many approaches for optimizing decision making systems rely on gradient based methods requiring informative feedback from the environment. However, in the case where such feedback is sparse or uninformative, such approaches may result in poor performance. Derivative-free approaches such as Bayesian Optimization mitigate the dependency on the quality of gradient feedback, but are known to scale poorly in the high-dimension setting of complex decision making systems. This problem is exacerbated if the system requires interactions between several actors cooperating to accomplish a shared goal. To address the dimensionality challenge, we propose a compact multi-layered architecture modeling the dynamics of actor interactions through the concept of role. We introduce Hessian-aware Bayesian Optimization to efficiently optimize the multi-layered architecture parameterized by a large number of parameters, and give the first improved regret bound in additive high-dimensional Bayesian Optimization since Mutny & Krause (2018). Our approach shows strong empirical results under malformed or sparse reward.

Foundation models (FMs), or large models pretrained on massive data then adapted for downstream tasks, have emerged as an effective paradigm in modern machine learning. The backbone of these FMs are often sequence models, operating on arbitrary sequences of inputs from a wide variety of domains such as language, images, speech, audio, time series, and genomics (Brown et al. 2020; Dosovitskiy et al. 2020; Ismail Fawaz et al. 2019; Oord et al. 2016; Poli et al. 2023; Sutskever, Vinyals, and Quoc V Le 2014). While this concept is agnostic to a particular choice of model architecture, modern FMs are predominantly based on a single type of sequence model: the Transformer (Vaswani et al. 2017) and its core attention layer (Bahdanau, Cho, and Bengio 2015) The efficacy of self-attention is attributed to its ability to route information densely within a context window, allowing it to model complex data. However, this property brings fundamental drawbacks: an inability to model anything outside of a finite window, and quadratic scaling with respect to the window length. An enormous body of research has appeared on more efficient variants of attention to overcome these drawbacks (Tay, Dehghani, Bahri, et al. 2022), but often at the expense of the very properties that makes it effective. As of yet, none of these variants have been shown to be empirically effective at scale across domains. Recently, structured state space sequence models (SSMs) (Gu, Goel, and Ré 2022; Gu, Johnson, Goel, et al. 2021) have emerged as a promising class of architectures for sequence modeling. These models can be interpreted as a combination of recurrent neural networks (RNNs) and convolutional neural networks (CNNs), with inspiration from classical state space models (Kalman 1960). This class of models can be computed very efficiently as either a recurrence or convolution, with linear or near-linear scaling in sequence length.

This paper delves into the problem of safe reinforcement learning (RL) in a partially observable environment with the aim of achieving safe-reachability objectives. In traditional partially observable Markov decision processes (POMDP), ensuring safety typically involves estimating the belief in latent states. However, accurately estimating an optimal Bayesian filter in POMDP to infer latent states from observations in a continuous state space poses a significant challenge, largely due to the intractable likelihood. To tackle this issue, we propose a stochastic model-based approach that guarantees RL safety almost surely in the face of unknown system dynamics and partial observation environments. We leveraged the Predictive State Representation (PSR) and Reproducing Kernel Hilbert Space (RKHS) to represent future multi-step observations analytically, and the results in this context are provable. Furthermore, we derived essential operators from the kernel Bayes' rule, enabling the recursive estimation of future observations using various operators. Under the assumption of \textit{undercompleness}, a polynomial sample complexity is established for the RL algorithm for the infinite size of observation and action spaces, ensuring an $\epsilon-$suboptimal safe policy guarantee.

Human activity recognition (HAR) is a key challenge in pervasive computing and its solutions have been presented based on various disciplines. Specifically, for HAR in a smart space without privacy and accessibility issues, data streams generated by deployed pervasive sensors are leveraged. In this paper, we focus on a group activity by which a group of users perform a collaborative task without user identification and propose an efficient group activity recognition scheme which extracts causality patterns from pervasive sensor event sequences generated by a group of users to support as good recognition accuracy as the state-of-the-art graphical model. To filter out irrelevant noise events from a given data stream, a set of rules is leveraged to highlight causally related events. Then, a pattern-tree algorithm extracts frequent causal patterns by means of a growing tree structure. Based on the extracted patterns, a weighted sum-based pattern matching algorithm computes the likelihoods of stored group activities to the given test event sequence by means of matched event pattern counts for group activity recognition. We evaluate the proposed scheme using the data collected from our testbed and CASAS datasets where users perform their tasks on a daily basis and validate its effectiveness in a real environment. Experiment results show that the proposed scheme performs higher recognition accuracy and with a small amount of runtime overhead than the existing schemes.