Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in large reasoning models. To analyze reasoning dynamics, we use synthetic logic puzzles as training data due to their controllable complexity and straightforward answer verification. We make some key technical contributions that lead to effective and stable RL training: a system prompt that emphasizes the thinking and answering process, a stringent format reward function that penalizes outputs for taking shortcuts, and a straightforward training recipe that achieves stable convergence. Our 7B model develops advanced reasoning skills-such as reflection, verification, and summarization-that are absent from the logic corpus. Remarkably, after training on just 5K logic problems, it demonstrates generalization abilities to the challenging math benchmarks AIME and AMC.

Many works have investigated reinforcement learning (RL) for routing and spectrum assignment on flex-grid networks but only one work to date has examined RL for fixed-grid with flex-rate transponders, despite production systems using this paradigm. Flex-rate transponders allow existing lightpaths to accommodate new services, a task we term routing and wavelength assignment with lightpath reuse (RWA-LR). We re-examine this problem and present a thorough benchmarking of heuristic algorithms for RWA-LR, which are shown to have 6% increased throughput when candidate paths are ordered by number of hops, rather than total length. We train an RL agent for RWA-LR with graph attention networks for the policy and value functions to exploit the graph-structured data. We provide details of our methodology and open source all of our code for reproduction. We outperform the previous state-of-the-art RL approach by 2.5% (17.4 Tbps mean additional throughput) and the best heuristic by 1.2% (8.5 Tbps mean additional throughput). This marginal gain highlights the difficulty in learning effective RL policies on long horizon resource allocation tasks.

Game-theoretic solution concepts, such as the Nash equilibrium, have been key to finding stable joint actions in multi-player games. However, it has been shown that the dynamics of agents' interactions, even in simple two-player games with few strategies, are incapable of reaching Nash equilibria, exhibiting complex and unpredictable behavior. Instead, evolutionary approaches can describe the long-term persistence of strategies and filter out transient ones, accounting for the long-term dynamics of agents' interactions. Our goal is to identify agents' joint strategies that result in stable behavior, being resistant to changes, while also accounting for agents' payoffs, in dynamic games. Towards this goal, and building on previous results, this paper proposes transforming dynamic games into their empirical forms by considering agents' strategies instead of agents' actions, and applying the evolutionary methodology $\alpha$-Rank to evaluate and rank strategy profiles according to their long-term dynamics. This methodology not only allows us to identify joint strategies that are strong through agents' long-term interactions, but also provides a descriptive, transparent framework regarding the high ranking of these strategies. Experiments report on agents that aim to collaboratively solve a stochastic version of the graph coloring problem. We consider different styles of play as strategies to define the empirical game, and train policies realizing these strategies, using the DQN algorithm. Then we run simulations to generate the payoff matrix required by $\alpha$-Rank to rank joint strategies.

The realization of scalable fault-tolerant quantum computing is expected to hinge on quantum error-correcting codes. In the quest for more efficient quantum fault tolerance, a critical code parameter is the weight of measurements that extract information about errors to enable error correction: as higher measurement weights require higher implementation costs and introduce more errors, it is important in code design to optimize measurement weight. This underlies the surging interest in quantum low-density parity-check (qLDPC) codes, the study of which has primarily focused on the asymptotic (large-code-limit) properties. In this work, we introduce a versatile and computationally efficient approach to stabilizer code weight reduction based on reinforcement learning (RL), which produces new low-weight codes that substantially outperform the state of the art in practically relevant parameter regimes, extending significantly beyond previously accessible small distances. For example, our approach demonstrates savings in physical qubit overhead compared to existing results by 1 to 2 orders of magnitude for weight 6 codes and brings the overhead into a feasible range for near-future experiments. We also investigate the interplay between code parameters using our RL framework, offering new insights into the potential efficiency and power of practically viable coding strategies. Overall, our results demonstrate how RL can effectively advance the crucial yet challenging problem of quantum code discovery and thereby facilitate a faster path to the practical implementation of fault-tolerant quantum technologies.

Model inversion attacks pose a significant privacy risk by attempting to reconstruct private training data from trained models. Most of the existing methods either depend on gradient estimation or require white-box access to model parameters, which limits their applicability in practical scenarios. In this paper, we propose PPO-MI, a novel reinforcement learning-based framework for black-box model inversion attacks. Our approach formulates the inversion task as a Markov Decision Process, where an agent navigates the latent space of a generative model to reconstruct private training samples using only model predictions. By employing Proximal Policy Optimization (PPO) with a momentum-based state transition mechanism, along with a reward function balancing prediction accuracy and exploration, PPO-MI ensures efficient latent space exploration and high query efficiency. W e conduct extensive experiments illustrates that PPO-MI outperforms the existing methods while require less attack knowledge, and it is robust across various model architectures and datasets. These results underline its effectiveness and generalizabil-ity in practical black-box scenarios, raising important considerations for the privacy vulnerabilities of deployed machine learning models.

We propose using reinforcement learning to address the challenges of discovering microarchitectural vulnerabilities, such as Spectre and Meltdown, which exploit subtle interactions in modern processors. Traditional methods like random fuzzing fail to efficiently explore the vast instruction space and often miss vulnerabilities that manifest under specific conditions. To overcome this, we introduce an intelligent, feedback-driven approach using RL. Our RL agents interact with the processor, learning from real-time feedback to prioritize instruction sequences more likely to reveal vulnerabilities, significantly improving the efficiency of the discovery process. We also demonstrate that RL systems adapt effectively to various microarchitectures, providing a scalable solution across processor generations. By automating the exploration process, we reduce the need for human intervention, enabling continuous learning that uncovers hidden vulnerabilities. Additionally, our approach detects subtle signals, such as timing anomalies or unusual cache behavior, that may indicate microarchitectural weaknesses. This proposal advances hardware security testing by introducing a more efficient, adaptive, and systematic framework for protecting modern processors. When unleashed on Intel Skylake-X and Raptor Lake microarchitectures, our RL agent was indeed able to generate instruction sequences that cause significant observable byte leakages through transient execution without generating any $\mu$code assists, faults or interrupts. The newly identified leaky sequences stem from a variety of Intel instructions, e.g. including SERIALIZE, VERR/VERW, CLMUL, MMX-x87 transitions, LSL+RDSCP and LAR. These initial results give credence to the proposed approach.

Deep reinforcement learning agents often face challenges to effectively coordinate perception and decision-making components, particularly in environments with high-dimensional sensory inputs where feature relevance varies. This work introduces SPRIG (Stackelberg Perception-Reinforcement learning with Internal Game dynamics), a framework that models the internal perception-policy interaction within a single agent as a cooperative Stackelberg game. In SPRIG, the perception module acts as a leader, strategically processing raw sensory states, while the policy module follows, making decisions based on extracted features. SPRIG provides theoretical guarantees through a modified Bellman operator while preserving the benefits of modern policy optimization. Experimental results on the Atari BeamRider environment demonstrate SPRIG's effectiveness, achieving around 30% higher returns than standard PPO through its game-theoretical balance of feature extraction and decision-making.

Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on trial-and-error poses challenges for real-world applications, as errors can result in costly and potentially damaging consequences. To address the need for safer learning, we propose a method that enables agents to learn goal-conditioned behaviors that explore without the risk of making harmful mistakes. Exploration without risks can seem paradoxical, but environment dynamics are often uniform in space, therefore a policy trained for safety without exploration purposes can still be exploited globally. Our proposed approach involves two distinct phases. First, during a pretraining phase, we employ safe reinforcement learning and distributional techniques to train a safety policy that actively tries to avoid failures in various situations. In the subsequent safe exploration phase, a goal-conditioned (GC) policy is learned while ensuring safety. To achieve this, we implement an action-selection mechanism leveraging the previously learned distributional safety critics to arbitrate between the safety policy and the GC policy, ensuring safe exploration by switching to the safety policy when needed. We evaluate our method in simulated environments and demonstrate that it not only provides substantial coverage of the goal space but also reduces the occurrence of mistakes to a minimum, in stark contrast to traditional GCRL approaches. Additionally, we conduct an ablation study and analyze failure modes, offering insights for future research directions.

Scalability remains a challenge in multi-agent reinforcement learning and is currently under active research. A framework named mean-field reinforcement learning (MFRL) could alleviate the scalability problem by employing the Mean Field Theory to turn a many-agent problem into a two-agent problem. However, this framework lacks the ability to identify essential interactions under nonstationary environments. Causality contains relatively invariant mechanisms behind interactions, though environments are nonstationary. Therefore, we propose an algorithm called causal mean-field Q-learning (CMFQ) to address the scalability problem. CMFQ is ever more robust toward the change of the number of agents though inheriting the compressed representation of MFRL's action-state space. Firstly, we model the causality behind the decision-making process of MFRL into a structural causal model (SCM). Then the essential degree of each interaction is quantified via intervening on the SCM. Furthermore, we design the causality-aware compact representation for behavioral information of agents as the weighted sum of all behavioral information according to their causal effects. We test CMFQ in a mixed cooperative-competitive game and a cooperative game. The result shows that our method has excellent scalability performance in both training in environments containing a large number of agents and testing in environments containing much more agents.

In this paper, we investigate the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy {\pi}. Prior works on statistical analysis of distributional TD learning mainly focus on the tabular case. In contrast, we first consider the linear function approximation setting and derive sharp finite-sample rates. Our theoretical results demonstrate that the sample complexity of linear distributional TD learning matches that of the classic linear TD learning. This implies that, with linear function approximation, learning the full distribution of the return using streaming data is no more difficult than learning its expectation (i.e. the value function). To derive tight sample complexity bounds, we conduct a fine-grained analysis of the linear-categorical Bellman equation, and employ the exponential stability arguments for products of random matrices. Our findings provide new insights into the statistical efficiency of distributional reinforcement learning algorithms.