Developing non-collaborative dialogue agents traditionally requires the manual, unscalable codification of expert strategies.We propose METRO, a method that leverages large language models to autonomously induce both strategy actions and planning logic directly from raw transcripts.METRO formalizes expert knowledge into a Strategy Forest, a hierarchical structure that captures both shortterm responses (nodes) and long-term strategic foresight (branches).Experimental results across two benchmarks show that METRO demonstrates promising performance, outperforming existing methods by an average of 9%-10%.Our further analysis not only reveals the success behind METRO (strategic behavioral diversity and foresight), but also demonstrates its robust cross-task transferability.This offers new insights into building non-collaborative agents in a cost-effective and scalable way.Our code is available at

Offline reinforcement learning (RL) aims to learn from static datasets and thus faces the challenge of value estimation errors for out-of-distribution actions. The in-sample learning scheme addresses this issue by performing implicit TD backups that does not query the values of unseen actions. However, pre-existing in-sample value learning and policy extraction methods suffer from over-regularization, limiting their performance on suboptimal or compositional datasets. In this paper, we analyze key factors in in-sample learning that might potentially hinder the use of a milder constraint. We propose Actor-Critic with Temperature adjustment and In-sample Value Ensemble (ACTIVE), a novel in-sample offline RL algorithm that leverages an ensemble of $V$-functions for critic training and adaptively adjusts the constraint level using dual gradient descent. We theoretically show that the $V$-ensemble suppresses the accumulation of initial value errors, thereby mitigating overestimation. Our experiments on the D4RL benchmarks demonstrate that ACTIVE alleviates overfitting of value functions and outperforms existing in-sample methods in terms of learning stability and policy optimality.

Deep learning methods incorporate PDE residuals as the loss function for solving Fokker-Planck equations, and usually impose the proper normalization condition to avoid a trivial solution. However, soft constraints require careful balancing of multi-objective loss functions, and specific network architectures may limit representation capacity under hard constraints. In this paper, we propose a novel framework: Fokker-Planck neural network (FPNN) that adopts a score PDE loss to decouple the score learning and the density normalization into two stages. Our method allows free-form network architectures to model the unnormalized density and strictly satisfy normalization constraints by post-processing. We demonstrate the effectiveness on various high-dimensional steady-state Fokker-Planck (SFP) equations, achieving superior accuracy and over a 20$\times$ speedup compared to state-of-the-art methods. Without any labeled data, FPNNs achieve the mean absolute percentage error (MAPE) of 11.36%, 13.87% and 12.72% for 4D Ring, 6D Unimodal and 6D Multi-modal problems respectively, requiring only 256, 980, and 980 parameters. Experimental results highlights the potential as a universal fast solver for handling more than 20-dimensional SFP equations, with great gains in efficiency, accuracy, memory and computational resource usage.

Offline Reinforcement Learning (RL) struggles with distributional shifts, leading to the $Q$-value overestimation for out-of-distribution (OOD) actions. Existing methods address this issue by imposing constraints; however, they often become overly conservative when evaluating OOD regions, which constrains the $Q$-function generalization. This over-constraint issue results in poor $Q$-value estimation and hinders policy improvement. In this paper, we introduce a novel approach to achieve better $Q$-value estimation by enhancing $Q$-function generalization in OOD regions within Convex Hull and its Neighborhood (CHN). Under the safety generalization guarantees of the CHN, we propose the Smooth Bellman Operator (SBO), which updates OOD $Q$-values by smoothing them with neighboring in-sample $Q$-values. We theoretically show that SBO approximates true $Q$-values for both in-sample and OOD actions within the CHN. Our practical algorithm, Smooth Q-function OOD Generalization (SQOG), empirically alleviates the over-constraint issue, achieving near-accurate $Q$-value estimation. On the D4RL benchmarks, SQOG outperforms existing state-of-the-art methods in both performance and computational efficiency. Code is available at <https://github.com/yqpqry/SQOG>.

Traditional threshold secret sharing scheme provides a mechanism to prevent the over-concentration of secrets while allowing for flexibility through the distribution and reconstruction of sub-secrets. However, this approach often simplifies participant behavior into categories of complete honesty or continuous deceit, neglecting the nuances of rational decision-making. To address this limitation, the rational secret sharing scheme merges threshold secret sharing with game theory, where each participant is considered rational and acts solely in self-interest. Nonetheless, existing schemes encounter challenges such as the prisoner's dilemma and the inability to reconstruct secrets due to the prioritization of individual interests. To mitigate these issues, our proposed scheme integrates a reward and punishment mechanism that balances short-term gains with long-term incentives, effectively deterring malicious behavior among participants. Moreover, traditional solutions based on elliptic curves and bilinear pairs lack resilience against quantum attacks. In response, our solution incorporates lattice-based cryptography to enhance security in the face of quantum threats. Additionally, we introduce an attribute access control tree to empower secret dealers in selecting suitable participants based on attribute restrictions, ensuring a more flexible, convenient, and secure rational secret sharing plan. This comprehensive approach improves participant selection and strengthens security measures in secret sharing scenarios.

Reinforcement learning (RL) with sparse and deceptive rewards is a significant challenge because nonzero rewards are rarely obtained, and hence, the gradient calculated by the agent can be stochastic and without valid information. Recent work demonstrates that using memory buffers of previous experiences can lead to a more efficient learning process. However, existing methods usually require these experiences to be successful and may overly exploit them, which can cause the agent to adopt suboptimal behaviors. This study develops an approach that exploits diverse past trajectories for faster and more efficient online RL, even if these trajectories are suboptimal or not highly rewarded. The proposed algorithm merges a policy improvement step with an additional policy exploration step by using offline demonstration data. The main contribution of this study is that by regarding diverse past trajectories as guidance, instead of imitating them, our method directs its policy to follow and expand past trajectories, while still being able to learn without rewards and gradually approach optimality. Furthermore, a novel diversity measurement is introduced to maintain the diversity of the team and regulate exploration. The proposed algorithm is evaluated on a series of discrete and continuous control tasks with sparse and deceptive rewards. In comparison with the existing RL methods, the experimental results indicate that our proposed algorithm is significantly better than the baseline methods in terms of diverse exploration and avoiding local optima.

Summary Ciphertext‐policy attribute‐based encryption (CP‐ABE) is regarded as one of the most suitable technologies for data access control in cloud storage system. It gives data owners direct and flexible control on access policies. However, there still exists practicality concerns in CP‐ABE applications, for example, the key escrow problem, user revocability, and large ciphertext size. Considering these problems, we propose a multi‐authority attribute‐based encryption scheme with constant‐size ciphertexts and user revocation for threshold access policy in this paper. The security proof shows that the proposed scheme is selectively secure under the augmented multi‐sequence of exponents decisional Diffie‐Hellman assumption, and it also achieves forward security, backward security, and collusion‐resistance.