Representations are at the core of all deep reinforcement learning (RL) methods for both Markov decision processes (MDPs) and partially observable Markov decision processes (POMDPs). Many representation learning methods and theoretical frameworks have been developed to understand what constitutes an effective representation. However, the relationships between these methods and the shared properties among them remain unclear. In this paper, we show that many of these seemingly distinct methods and frameworks for state and history abstractions are, in fact, based on a common idea of self-predictive abstraction. Furthermore, we provide theoretical insights into the widely adopted objectives and optimization, such as the stop-gradient technique, in learning self-predictive representations. These findings together yield a minimalist algorithm to learn self-predictive representations for states and histories. We validate our theories by applying our algorithm to standard MDPs, MDPs with distractors, and POMDPs with sparse rewards. These findings culminate in a set of practical guidelines for RL practitioners.

Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent reinforcement learning, to tackle this challenge. This study delves deep into the effects of this value-decomposition, revealing that whilst it curtails the over-estimation bias inherent to Q-learning algorithms, it amplifies target variance. To counteract this, we present an ensemble of critics to mitigate target variance. Moreover, we introduce a regularisation loss that helps to mitigate the effects that exploratory actions in one dimension can have on the value of optimal actions in other dimensions. Our novel algorithm, REValueD, tested on discretised versions of the DeepMind Control Suite tasks, showcases superior performance, especially in the challenging humanoid and dog tasks. We further dissect the factors influencing REValueD's performance, evaluating the significance of the regularisation loss and the scalability of REValueD with increasing sub-actions per dimension.

Offline reinforcement learning (RL) offers a promising direction for learning policies from pre-collected datasets without requiring further interactions with the environment. However, existing methods struggle to handle out-of-distribution (OOD) extrapolation errors, especially in sparse reward or scarce data settings. In this paper, we propose a novel training algorithm called Conservative Density Estimation (CDE), which addresses this challenge by explicitly imposing constraints on the state-action occupancy stationary distribution. CDE overcomes the limitations of existing approaches, such as the stationary distribution correction method, by addressing the support mismatch issue in marginal importance sampling. Our method achieves state-of-the-art performance on the D4RL benchmark. Notably, CDE consistently outperforms baselines in challenging tasks with sparse rewards or insufficient data, demonstrating the advantages of our approach in addressing the extrapolation error problem in offline RL.

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered third-person-view vision models, but its application to embodied egocentric perception tasks remains largely unexplored. A critical challenge lies in simulating natural human movements and behaviors that effectively steer the embodied cameras to capture a faithful egocentric representation of the 3D world. To address this challenge, we introduce EgoGen, a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. Combined with collision-avoiding motion primitives and a two-stage reinforcement learning approach, our motion synthesis model offers a closed-loop solution where the embodied perception and movement of the virtual human are seamlessly coupled. Compared to previous works, our model eliminates the need for a pre-defined global path, and is directly applicable to dynamic environments. Combined with our easy-to-use and scalable data generation pipeline, we demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views. EgoGen will be fully open-sourced, offering a practical solution for creating realistic egocentric training data and aiming to serve as a useful tool for egocentric computer vision research. Refer to our project page: https://ego-gen.github.io/.

In this paper, we employ active simultaneously transmitting and reflecting reconfigurable intelligent surface (ASRIS) to aid in establishing and enhancing communication within a commensal symbiotic radio (CSR) network. Unlike traditional RIS, ASRIS not only ensures coverage in an omni directional manner but also amplifies received signals, consequently elevating overall network performance. in the first phase, base station (BS) with active massive MIMO antennas, send ambient signal to SBDs. In the first phase, the BS transmits ambient signals to the symbiotic backscatter devices (SBDs), and after harvesting the energy and modulating their information onto the signal carrier, the SBDs send Backscatter signals back to the BS. In this scheme, we employ the Backscatter Relay system to facilitate the transmission of information from the SBDs to the symbiotic User Equipments (SUEs) with the assistance of the BS. In the second phase, the BS transmits information signals to the SUEs after eliminating interference using the Successive Interference Cancellation (SIC) method. ASRIS is employed to establish communication among SUEs lacking a line of sight (LoS) and to amplify power signals for SUEs with a LoS connection to the BS. It is worth noting that we use NOMA for multiple access in all network. The main goal of this paper is to maximize the sum throughput between all users. To achieve this, we formulate an optimization problem with variables including active beamforming coefficients at the BS and ASRIS, as well as the phase adjustments of ASRIS and scheduling parameters between the first and second phases. To model this optimization problem, we employ three deep reinforcement learning (DRL) methods, namely PPO, TD3, and A3C. Finally, the mentioned methods are simulated and compared with each other.

Conversational question answering (ConvQA) over law knowledge bases (KBs) involves answering multi-turn natural language questions about law and hope to find answers in the law knowledge base. Despite many methods have been proposed. Existing law knowledge base ConvQA model assume that the input question is clear and can perfectly reflect user's intention. However, in real world, the input questions are noisy and inexplict. This makes the model hard to find the correct answer in the law knowledge bases. In this paper, we try to use reinforcement learning to solve this problem. The reinforcement learning agent can automatically learn how to find the answer based on the input question and the conversation history, even when the input question is inexplicit. We test the proposed method on several real world datasets and the results show the effectivenss of the proposed model.

This research delves into the role of the quantum Fisher Information Matrix (FIM) in enhancing the performance of Parameterized Quantum Circuit (PQC)-based reinforcement learning agents. While previous studies have highlighted the effectiveness of PQC-based policies preconditioned with the quantum FIM in contextual bandits, its impact in broader reinforcement learning contexts, such as Markov Decision Processes, is less clear. Through a detailed analysis of L\"owner inequalities between quantum and classical FIMs, this study uncovers the nuanced distinctions and implications of using each type of FIM. Our results indicate that a PQC-based agent using the quantum FIM without additional insights typically incurs a larger approximation error and does not guarantee improved performance compared to the classical FIM. Empirical evaluations in classic control benchmarks suggest even though quantum FIM preconditioning outperforms standard gradient ascent, in general it is not superior to classical FIM preconditioning.

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion. This manual procedure can be time consuming, ineffective, and the generated prompts are, in a lot of cases, sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications? To address these questions, in this paper, we investigate prompt engineering automation. We consider a specific use case scenario in which developers/users have drafted initial prompts, but lack the time/expertise to optimize them. We propose PRewrite, an automated tool to rewrite these drafts and to generate highly effective new prompts. PRewrite is based on the Reinforcement Learning (RL) framework which allows for end-to-end optimization and our design allows the RL search to happen in a large action space. The automated tool leverages manually crafted prompts as starting points which makes the rewriting procedure more guided and efficient. The generated prompts are human readable, and self-explanatory, unlike some of those in previous works. We conducted extensive experiments on diverse datasets and found that the prompts generated with this new method not only outperform professionally crafted prompts, but also prompts generated with other previously proposed methods.

This study introduces CycLight, a novel cycle-level deep reinforcement learning (RL) approach for network-level adaptive traffic signal control (NATSC) systems. Unlike most traditional RL-based traffic controllers that focus on step-by-step decision making, CycLight adopts a cycle-level strategy, optimizing cycle length and splits simultaneously using Parameterized Deep Q-Networks (PDQN) algorithm. This cycle-level approach effectively reduces the computational burden associated with frequent data communication, meanwhile enhancing the practicality and safety of real-world applications. A decentralized framework is formulated for multi-agent cooperation, while attention mechanism is integrated to accurately assess the impact of the surroundings on the current intersection. CycLight is tested in a large synthetic traffic grid using the microscopic traffic simulation tool, SUMO. Experimental results not only demonstrate the superiority of CycLight over other state-of-the-art approaches but also showcase its robustness against information transmission delays.

Chiplet-based systems have gained significant attention in recent years due to their low cost and competitive performance. As the complexity and compactness of a chiplet-based system increase, careful consideration must be given to microbump assignments, interconnect delays, and thermal limitations during the floorplanning stage. This paper introduces RLPlanner, an efficient early-stage floorplanning tool for chiplet-based systems with a novel fast thermal evaluation method. RLPlanner employs advanced reinforcement learning to jointly minimize total wirelength and temperature. To alleviate the time-consuming thermal calculations, RLPlanner incorporates the developed fast thermal evaluation method to expedite the iterations and optimizations. Comprehensive experiments demonstrate that our proposed fast thermal evaluation method achieves a mean absolute error (MAE) of 0.25 K and delivers over 120x speed-up compared to the open-source thermal solver HotSpot. When integrated with our fast thermal evaluation method, RLPlanner achieves an average improvement of 20.28\% in minimizing the target objective (a combination of wirelength and temperature), within a similar running time, compared to the classic simulated annealing method with HotSpot.