Generalization in Deep Reinforcement Learning across unseen environment variations often requires training over a diverse set of scenarios. However, random task partitioning in GSL can impede specialist performance, as it often assigns vastly different variations to the same specialist, typically resulting in each specialist being assigned just one variation, which increases computational costs. To improve this, we propose Generalist-Specialist Learning with Point Cloud Featurebased Task Partitioning (GSL-PCD). This approach clusters environment variations based on features extracted from object point clouds, using balanced clustering with a greedy algorithm to assign similar variations to the same specialist. Evaluations on robotic manipulation tasks from the ManiSkill benchmark demonstrate that point cloud feature-based partitioning outperforms vanilla partitioning by 9.4% with a fixed number of specialists and reduces computational and sample requirements by 50% to achieve comparable performance.

As a fundamental sports discipline, track and field not In recent years, real-time monitoring and data analysis only forms the core of major events like the Olympics have become increasingly critical in enhancing athletic and World Championships but also plays a crucial role in performance. Studies have shown that by monitoring physiological promoting public health Jacobsson, Ekberg, Timpka, Haggren indicators (such as heart rate, body temperature, and Råsberg, Sjöberg, Mirkovic and Nilsson (2020); Timpka, blood oxygen saturation) and performance metrics (such as Dahlström, Fagher, Adami, Andersson, Jacobsson, Svedin speed, acceleration, and force) in real-time, it is possible to and Bermon (2022). The wide variety of track and field events, identify problems during training promptly and make targeted including sprints, middle and long-distance running, jumps, adjustments. For example, analyzing heart rate changes under and throws, demand high levels of physical fitness, technical different training intensities can assess endurance levels and skills, and mental strength from athletes Guo (2022); Zhang recovery status, while monitoring gait and acceleration during et al. (2023a). To excel in such competitive environments, running can optimize technical movements and improve athletes require not only innate talent and dedication but efficiency Rana and Mittal (2020a). Many studies have begun also scientific and systematic training methods Zhang et al. exploring the potential of using sensor technology and data (2023b); Yuan et al. (2024).

Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minimizing projected Bellman error and min-max optimization, cannot be modelled as minimizing a scalar loss function but instead correspond to solving a variational inequality (VI) problem. This difference in setting has caused many practical challenges as naive gradient-based approaches from supervised learning tend to diverge and cycle in the VI case. In this work, we propose a principled surrogate-based approach compatible with deep learning to solve VIs. We show that our surrogate-based approach has three main benefits: (1) under assumptions that are realistic in practice (when hidden monotone structure is present, interpolation, and sufficient optimization of the surrogates), it guarantees convergence, (2) it provides a unifying perspective of existing methods, and (3) is amenable to existing deep learning optimizers like ADAM. Experimentally, we demonstrate our surrogate-based approach is effective in min-max optimization and minimizing projected Bellman error. Furthermore, in the deep reinforcement learning case, we propose a novel variant of TD(0) which is more compute and sample efficient.

Cryptocurrencies have gained popularity due to their transparency, security, and accessibility compared to traditional financial systems, with Bitcoin, introduced in 2009, leading the market. Bitcoin's security relies on blockchain technology - a decentralized ledger consisting of a consensus and an incentive mechanism. The consensus mechanism, Proof of Work (PoW), requires miners to solve difficult cryptographic puzzles to add new blocks, while the incentive mechanism rewards them with newly minted bitcoins. However, as Bitcoin's acceptance grows, it faces increasing threats from attacks targeting these mechanisms, such as selfish mining, double-spending, and block withholding. These attacks compromise security, efficiency, and reward distribution. Recent research shows that these attacks can be combined with each other or with either malicious strategies, such as network-layer attacks, or non-malicious strategies, like honest mining. These combinations lead to more sophisticated attacks, increasing the attacker's success rates and profitability. Therefore, understanding and evaluating these attacks is essential for developing effective countermeasures and ensuring long-term security. This paper begins by examining individual attacks executed in isolation and their profitability. It then explores how combining these attacks with each other or with other malicious and non-malicious strategies can enhance their overall effectiveness and profitability. The analysis further explores how the deployment of attacks such as selfish mining and block withholding by multiple competing mining pools against each other impacts their economic returns. Lastly, a set of design guidelines is provided, outlining areas future work should focus on to prevent or mitigate the identified threats.

Quantum Tiq-Taq-Toe is a well-known benchmark and playground for both quantum computing and machine learning. Despite its popularity, no reinforcement learning (RL) methods have been applied to Quantum Tiq-Taq-Toe. Although there has been some research on Quantum Chess this game is significantly more complex in terms of computation and analysis. Therefore, we study the combination of quantum computing and reinforcement learning in Quantum Tiq-Taq-Toe, which may serve as an accessible testbed for the integration of both fields. Quantum games are challenging to represent classically due to their inherent partial observability and the potential for exponential state complexity. In Quantum Tiq-Taq-Toe, states are observed through Measurement (a 3x3 matrix of state probabilities) and Move History (a 9x9 matrix of entanglement relations), making strategy complex as each move can collapse the quantum state.

Fast-converging algorithms are a contemporary requirement in reinforcement learning. In the context of linear function approximation, the magnitude of the smallest eigenvalue of the key matrix is a major factor reflecting the convergence speed. Traditional value-based RL algorithms focus on minimizing errors. This paper introduces a variance minimization (VM) approach for value-based RL instead of error minimization. Based on this approach, we proposed two objectives, the Variance of Bellman Error (VBE) and the Variance of Projected Bellman Error (VPBE), and derived the VMTD, VMTDC, and VMETD algorithms. We provided proofs of their convergence and optimal policy invariance of the variance minimization. Experimental studies validate the effectiveness of the proposed algorithms.

Traffic signal control is crucial for managing congestion in urban networks. Existing myopic pressure-based control methods focus only on immediate upstream links, leading to suboptimal green time allocation and increased network delays. Effective signal control, however, inherently requires a broader spatial scope, as traffic conditions further upstream can significantly impact traffic at the current location. This paper introduces a novel concept based on the Markov chain theory, namely multi-hop upstream pressure, that generalizes the conventional pressure to account for traffic conditions beyond the immediate upstream links. This farsighted and compact metric informs the deep reinforcement learning agent to preemptively clear the present queues, guiding the agent to optimize signal timings with a broader spatial awareness. Simulations on synthetic and realistic (Toronto) scenarios demonstrate controllers utilizing multi-hop upstream pressure significantly reduce overall network delay by prioritizing traffic movements based on a broader understanding of upstream congestion.

This study investigates the development of an optimal execution strategy through reinforcement learning, aiming to determine the most effective approach for traders to buy and sell inventory within a limited time frame. Our proposed model leverages input features derived from the current state of the limit order book. To simulate this environment and overcome the limitations associated with relying on historical data, we utilize the multi-agent market simulator ABIDES, which provides a diverse range of depth levels within the limit order book. We present a custom MDP formulation followed by the results of our methodology and benchmark the performance against standard execution strategies. Our findings suggest that the reinforcement learning-based approach demonstrates significant potential.

We consider the problem of learning an $\varepsilon$-optimal policy in controlled dynamical systems with low-rank latent structure. For this problem, we present LoRa-PI (Low-Rank Policy Iteration), a model-free learning algorithm alternating between policy improvement and policy evaluation steps. In the latter, the algorithm estimates the low-rank matrix corresponding to the (state, action) value function of the current policy using the following two-phase procedure. The entries of the matrix are first sampled uniformly at random to estimate, via a spectral method, the leverage scores of its rows and columns. These scores are then used to extract a few important rows and columns whose entries are further sampled. The algorithm exploits these new samples to complete the matrix estimation using a CUR-like method. For this leveraged matrix estimation procedure, we establish entry-wise guarantees that remarkably, do not depend on the coherence of the matrix but only on its spikiness. These guarantees imply that LoRa-PI learns an $\varepsilon$-optimal policy using $\widetilde{O}({S+A\over \mathrm{poly}(1-\gamma)\varepsilon^2})$ samples where $S$ (resp. $A$) denotes the number of states (resp. actions) and $\gamma$ the discount factor. Our algorithm achieves this order-optimal (in $S$, $A$ and $\varepsilon$) sample complexity under milder conditions than those assumed in previously proposed approaches.

While reinforcement learning (RL) agents often perform well during training, they can struggle with distribution shift in real-world deployments. One particularly severe risk of distribution shift is goal misgeneralization, where the agent learns a proxy goal that coincides with the true goal during training but not during deployment. In this paper, we explore whether allowing an agent to ask for help from a supervisor in unfamiliar situations can mitigate this issue. We focus on agents trained with PPO in the CoinRun environment, a setting known to exhibit goal misgeneralization. We evaluate multiple methods for determining when the agent should request help and find that asking for help consistently improves performance. However, we also find that methods based on the agent's internal state fail to proactively request help, instead waiting until mistakes have already occurred. Further investigation suggests that the agent's internal state does not represent the coin at all, highlighting the importance of learning nuanced representations, the risks of ignoring everything not immediately relevant to reward, and the necessity of developing ask-for-help strategies tailored to the agent's training algorithm.