Policy Mirror Descent (PMD) stands as a versatile algorithmic framework encompassing several seminal policy gradient algorithms such as natural policy gradient, with connections with state-of-the-art reinforcement learning (RL) algorithms such as TRPO and PPO. PMD can be seen as a soft Policy Iteration algorithm implementing regularized 1-step greedy policy improvement. However, 1-step greedy policies might not be the best choice and recent remarkable empirical successes in RL such as AlphaGo and AlphaZero have demonstrated that greedy approaches with respect to multiple steps outperform their 1-step counterpart. In this work, we propose a new class of PMD algorithms called $h$-PMD which incorporates multi-step greedy policy improvement with lookahead depth $h$ to the PMD update rule. To solve discounted infinite horizon Markov Decision Processes with discount factor $\gamma$, we show that $h$-PMD which generalizes the standard PMD enjoys a faster dimension-free $\gamma^h$-linear convergence rate, contingent on the computation of multi-step greedy policies. We propose an inexact version of $h$-PMD where lookahead action values are estimated. Under a generative model, we establish a sample complexity for $h$-PMD which improves over prior work. Finally, we extend our result to linear function approximation to scale to large state spaces. Under suitable assumptions, our sample complexity only involves dependence on the dimension of the feature map space instead of the state space size.

The AAAI/SIGAI Doctoral Consortium provides an opportunity for a group of PhD students to discuss and explore their research interests and career objectives in an interdisciplinary workshop together with a panel of established researchers. This year, 30 students were selected for this programme, and we've been meeting them and talking about their research. In this interview, Raffaele Galliera, tells us about his work on deep reinforcement learning for communication networks. My name is Raffaele Galliera and I'm a PhD student in the Intelligent Systems and Robotics program at the University of West Florida, located in Pensacola. It's a joint program between the University of West Florida and the Institute for Human and Machine Cognition (IHMC), which is a nonprofit organization based in Pensacola.

We study pre-training representations for decision-making using video data, which is abundantly available for tasks such as game agents and software testing. Even though significant empirical advances have been made on this problem, a theoretical understanding remains absent. We initiate the theoretical investigation into principled approaches for representation learning and focus on learning the latent state representations of the underlying MDP using video data. We study two types of settings: one where there is iid noise in the observation, and a more challenging setting where there is also the presence of exogenous noise, which is non-iid noise that is temporally correlated, such as the motion of people or cars in the background. We study three commonly used approaches: autoencoding, temporal contrastive learning, and forward modeling. We prove upper bounds for temporal contrastive learning and forward modeling in the presence of only iid noise. We show that these approaches can learn the latent state and use it to do efficient downstream RL with polynomial sample complexity. When exogenous noise is also present, we establish a lower bound result showing that the sample complexity of learning from video data can be exponentially worse than learning from action-labeled trajectory data. This partially explains why reinforcement learning with video pre-training is hard. We evaluate these representational learning methods in two visual domains, yielding results that are consistent with our theoretical findings.

In this work, we propose an approach to generalize denoising diffusion probabilistic models for stock market predictions and portfolio management. Present works have demonstrated the efficacy of modeling interstock relations for market time-series forecasting and utilized Graph-based learning models for value prediction and portfolio management. Though convincing, these deterministic approaches still fall short of handling uncertainties i.e., due to the low signal-to-noise ratio of the financial data, it is quite challenging to learn effective deterministic models. Since the probabilistic methods have shown to effectively emulate higher uncertainties for time-series predictions. To this end, we showcase effective utilisation of Denoising Diffusion Probabilistic Models (DDPM), to develop an architecture for providing better market predictions conditioned on the historical financial indicators and inter-stock relations. Additionally, we also provide a novel deterministic architecture MaTCHS which uses Masked Relational Transformer(MRT) to exploit inter-stock relations along with historical stock features. We demonstrate that our model achieves SOTA performance for movement predication and Portfolio management.

In this paper, we study the problem of multi-reward reinforcement learning to jointly optimize for multiple text qualities for natural language generation. We focus on the task of counselor reflection generation, where we optimize the generators to simultaneously improve the fluency, coherence, and reflection quality of generated counselor responses. We introduce two novel bandit methods, DynaOpt and C-DynaOpt, which rely on the broad strategy of combining rewards into a single value and optimizing them simultaneously. Specifically, we employ non-contextual and contextual multi-arm bandits to dynamically adjust multiple reward weights during training. Through automatic and manual evaluations, we show that our proposed techniques, DynaOpt and C-DynaOpt, outperform existing naive and bandit baselines, demonstrating their potential for enhancing language models.

Deep reinforcement learning has made significant progress in games with imperfect information, but its performance in the card game Doudizhu (Chinese Poker/Fight the Landlord) remains unsatisfactory. Doudizhu is different from conventional games as it involves three players and combines elements of cooperation and confrontation, resulting in a large state and action space. In 2021, a Doudizhu program called DouZero\cite{zha2021douzero} surpassed previous models without prior knowledge by utilizing traditional Monte Carlo methods and multilayer perceptrons. Building on this work, our study incorporates residual networks into the model, explores different architectural designs, and conducts multi-role testing. Our findings demonstrate that this model significantly improves the winning rate within the same training time. Additionally, we introduce a call scoring system to assist the agent in deciding whether to become a landlord. With these enhancements, our model consistently outperforms the existing version of DouZero and even experienced human players. \footnote{The source code is available at \url{https://github.com/Yingchaol/Douzero_Resnet.git.}

The paragraph is grammatically correct and logically coherent. It discusses the importance of mobile terminal cloud computing migration technology in meeting the demands of evolving computer and cloud computing technologies. It emphasizes the need for efficient data access and storage, as well as the utilization of cloud computing migration technology to prevent additional time delays. The paragraph also highlights the contributions of cloud computing migration technology to expanding cloud computing services. Additionally, it acknowledges the role of virtualization as a fundamental capability of cloud computing while emphasizing that cloud computing and virtualization are not inherently interconnected. Finally, it introduces machine learning-based virtual machine migration optimization and dynamic resource allocation as a critical research direction in cloud computing, citing the limitations of static rules or manual settings in traditional cloud computing environments. Overall, the paragraph effectively communicates the importance of machine learning technology in addressing resource allocation and virtual machine migration challenges in cloud computing.

In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective search) for online testing of Deep Neural Network-enabled systems. The empirical evaluation of these techniques was conducted on a state-of-the-art Autonomous Driving System (ADS). This work is a replication and extension of that empirical study. Our replication shows that RL does not outperform pure random test generation in a comparison conducted under the same settings of the original study, but with no confounding factor coming from the way collisions are measured. Our extension aims at eliminating some of the possible reasons for the poor performance of RL observed in our replication: (1) the presence of reward components providing contrasting or useless feedback to the RL agent; (2) the usage of an RL algorithm (Q-learning) which requires discretization of an intrinsically continuous state space. Results show that our new RL agent is able to converge to an effective policy that outperforms random testing. Results also highlight other possible improvements, which open to further investigations on how to best leverage RL for online ADS testing.

Traffic signal control is important in intelligent transportation system, of which cooperative control is difficult to realize but yet vital. Many methods model multi-intersection traffic networks as grids and address the problem using multi-agent reinforcement learning (RL). Despite these existing studies, there is an opportunity to further enhance our understanding of the connectivity and globality of the traffic networks by capturing the spatiotemporal traffic information with efficient neural networks in deep RL. In this paper, we propose a novel multi-agent actor-critic framework based on an interpretable influence mechanism with a centralized learning and decentralized execution method. Specifically, we first construct an actor-critic framework, for which the piecewise linear neural network (PWLNN), named biased ReLU (BReLU), is used as the function approximator to obtain a more accurate and theoretically grounded approximation. Finally, our proposed framework is validated on two synthetic traffic networks to coordinate signal control between intersections, achieving lower traffic delays across the entire traffic network compared to state-of-the-art (SOTA) performance.

This paper presents a novel reinforcement learning (RL) approach called HAAM-RL (Heuristic Algorithm-based Action Masking Reinforcement Learning) for optimizing the color batching re-sequencing problem in automobile painting processes. The existing heuristic algorithms have limitations in adequately reflecting real-world constraints and accurately predicting logistics performance. Our methodology incorporates several key techniques including a tailored Markov Decision Process (MDP) formulation, reward setting including Potential-Based Reward Shaping, action masking using heuristic algorithms (HAAM-RL), and an ensemble inference method that combines multiple RL models. The RL agent is trained and evaluated using FlexSim, a commercial 3D simulation software, integrated with our RL MLOps platform BakingSoDA. Experimental results across 30 scenarios demonstrate that HAAM-RL with an ensemble inference method achieves a 16.25% performance improvement over the conventional heuristic algorithm, with stable and consistent results. The proposed approach exhibits superior performance and generalization capability, indicating its effectiveness in optimizing complex manufacturing processes. The study also discusses future research directions, including alternative state representations, incorporating model-based RL methods, and integrating additional real-world constraints.