Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation, but this turns out to be ineffective in maintaining safety constraints with high probability. To this end, we move to the quantile-constrained RL that enables a higher level of safety without any expectation-form approximations. We directly estimate the quantile gradients through sampling and provide the theoretical proofs of convergence. Then a tilted update strategy for quantile gradients is implemented to compensate the asymmetric distributional density, with a direct benefit of return performance. Experiments demonstrate that the proposed model fully meets safety requirements (quantile constraints) while outperforming the state-of-the-art benchmarks with higher return.

The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term memory and dependency. The reward sparseness problem is further amplified in non-Markovian scenarios. Hence learning a non-Markovian task (NMT) is inherently more difficult than learning a Markovian one. In this paper, we propose a novel \textbf{Par}allel and \textbf{Mod}ular RL framework, ParMod, specifically for learning NMTs specified by temporal logic. With the aid of formal techniques, the NMT is modulaized into a series of sub-tasks based on the automaton structure (equivalent to its temporal logic counterpart). On this basis, sub-tasks will be trained by a group of agents in a parallel fashion, with one agent handling one sub-task. Besides parallel training, the core of ParMod lies in: a flexible classification method for modularizing the NMT, and an effective reward shaping method for improving the sample efficiency. A comprehensive evaluation is conducted on several challenging benchmark problems with respect to various metrics. The experimental results show that ParMod achieves superior performance over other relevant studies. Our work thus provides a good synergy among RL, NMT and temporal logic.

Online advertising has become one of the most successful business models of the internet era. Impression opportunities are typically allocated through real-time auctions, where advertisers bid to secure advertisement slots. Deciding the best bid for an impression opportunity is challenging, due to the stochastic nature of user behavior and the variability of advertisement traffic over time. In this work, we propose a framework for training auto-bidding agents in multi-slot second-price auctions to maximize acquisitions (e.g., clicks, conversions) while adhering to budget and cost-per-acquisition (CPA) constraints. We exploit the insight that, after an advertisement campaign concludes, determining the optimal bids for each impression opportunity can be framed as a multiple-choice knapsack problem (MCKP) with a nonlinear objective. We propose an "oracle" algorithm that identifies a near-optimal combination of impression opportunities and advertisement slots, considering both past and future advertisement traffic data. This oracle solution serves as a training target for a student network which bids having access only to real-time information, a method we term Oracle Imitation Learning (OIL). Through numerical experiments, we demonstrate that OIL achieves superior performance compared to both online and offline reinforcement learning algorithms, offering improved sample efficiency. Notably, OIL shifts the complexity of training auto-bidding agents from crafting sophisticated learning algorithms to solving a nonlinear constrained optimization problem efficiently.

This paper proposes a new design method for a stochastic control policy using a normalizing flow (NF). In reinforcement learning (RL), the policy is usually modeled as a distribution model with trainable parameters. When this parameterization has less expressiveness, it would fail to acquiring the optimal policy. A mixture model has capability of a universal approximation, but it with too much redundancy increases the computational cost, which can become a bottleneck when considering the use of real-time robot control. As another approach, NF, which is with additional parameters for invertible transformation from a simple stochastic model as a base, is expected to exert high expressiveness and lower computational cost. However, NF cannot compute its mean analytically due to complexity of the invertible transformation, and it lacks reliability because it retains stochastic behaviors after deployment for robot controller. This paper therefore designs a restricted NF (RNF) that achieves an analytic mean by appropriately restricting the invertible transformation. In addition, the expressiveness impaired by this restriction is regained using bimodal student-t distribution as its base, so-called Bit-RNF. In RL benchmarks, Bit-RNF policy outperformed the previous models. Finally, a real robot experiment demonstrated the applicability of Bit-RNF policy to real world. The attached video is uploaded on youtube: https://youtu.be/R_GJVZDW9bk

The increasing deployment of AI models in critical applications has exposed them to significant risks from adversarial attacks. While adversarial vulnerabilities in 2D vision models have been extensively studied, the threat landscape for 3D generative models, such as Neural Radiance Fields (NeRF), remains underexplored. This work introduces \textit{AdvIRL}, a novel framework for crafting adversarial NeRF models using Instant Neural Graphics Primitives (Instant-NGP) and Reinforcement Learning. Unlike prior methods, \textit{AdvIRL} generates adversarial noise that remains robust under diverse 3D transformations, including rotations and scaling, enabling effective black-box attacks in real-world scenarios. Our approach is validated across a wide range of scenes, from small objects (e.g., bananas) to large environments (e.g., lighthouses). Notably, targeted attacks achieved high-confidence misclassifications, such as labeling a banana as a slug and a truck as a cannon, demonstrating the practical risks posed by adversarial NeRFs. Beyond attacking, \textit{AdvIRL}-generated adversarial models can serve as adversarial training data to enhance the robustness of vision systems. The implementation of \textit{AdvIRL} is publicly available at \url{https://github.com/Tommy-Nguyen-cpu/AdvIRL/tree/MultiView-Clean}, ensuring reproducibility and facilitating future research.

Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex closed-box policies that are effective, but suffer from an inherent opacity. Interpretable policies, while generally underperforming compared to their closed-box counterparts, advantageously facilitate transparent decision-making within automated systems. Hence, their usage is often essential for diagnosing and mitigating errors, supporting ethical and legal accountability, and fostering trust among stakeholders. In this paper, we propose SMOSE, a novel method to train sparsely activated interpretable controllers, based on a top-1 Mixture-of-Experts architecture. SMOSE combines a set of interpretable decisionmakers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts. The training is carried out via state-of-the-art Reinforcement Learning algorithms, exploiting load-balancing techniques to ensure fair expert usage. We then distill decision trees from the weights of the router, significantly improving the ease of interpretation. We evaluate SMOSE on six benchmark environments from MuJoCo: our method outperforms recent interpretable baselines and narrows the gap with noninterpretable state-of-the-art algorithms

This paper enables real-world humanoid robots to maintain stability while performing expressive motions like humans do. We propose ExBody2, a generalized whole-body tracking framework that can take any reference motion inputs and control the humanoid to mimic the motion. The model is trained in simulation with Reinforcement Learning and then transferred to the real world. It decouples keypoint tracking with velocity control, and effectively leverages a privileged teacher policy to distill precise mimic skills into the target student policy, which enables high-fidelity replication of dynamic movements such as running, crouching, dancing, and other challenging motions. We present a comprehensive qualitative and quantitative analysis of crucial design factors in the paper. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-arts, providing practical guidelines to pursue the extreme of whole-body control for humanoid robots.

Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a control policy together with a certificate function for the property. Popular examples include barrier functions for safety and Lyapunov functions for asymptotic stability. While there has been significant progress on learning-based control with certificate functions in the white-box setting, where the correctness of the certificate function can be formally verified, there has been little work on ensuring their reliability in the black-box setting where the system dynamics are unknown. In this work, we consider the problems of certifying and repairing neural network control policies and certificate functions in the black-box setting. We propose a novel framework that utilizes runtime monitoring to detect system behaviors that violate the property of interest under some initially trained neural network policy and certificate. These violating behaviors are used to extract new training data, that is used to re-train the neural network policy and the certificate function and to ultimately repair them. We demonstrate the effectiveness of our approach empirically by using it to repair and to boost the safety rate of neural network policies learned by a state-of-the-art method for learning-based control on two autonomous system control tasks.

This paper surveys research in the rapidly growing field of enhancing large language models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve their performance by receiving feedback in the form of rewards based on the quality of their outputs, allowing them to generate more accurate, coherent, and contextually appropriate responses. In this work, we make a systematic review of the most up-to-date state of knowledge on RL-enhanced LLMs, attempting to consolidate and analyze the rapidly growing research in this field, helping researchers understand the current challenges and advancements. Specifically, we (1) detail the basics of RL; (2) introduce popular RL-enhanced LLMs; (3) review researches on two widely-used reward model-based RL techniques: Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF); and (4) explore Direct Preference Optimization (DPO), a set of methods that bypass the reward model to directly use human preference data for aligning LLM outputs with human expectations. We will also point out current challenges and deficiencies of existing methods and suggest some avenues for further improvements. Project page of this work can be found at: \url{https://github.com/ShuheWang1998/Reinforcement-Learning-Enhanced-LLMs-A-Survey}.

Tasks in which rewards depend upon past information not available in the current observation set can only be solved by agents that are equipped with short-term memory. Usual choices for memory modules include trainable recurrent hidden layers, often with gated memory. Reservoir computing presents an alternative, in which a recurrent layer is not trained, but rather has a set of fixed, sparse recurrent weights. The weights are scaled to produce stable dynamical behavior such that the reservoir state contains a high-dimensional, nonlinear impulse response function of the inputs. An output decoder network can then be used to map the compressive history represented by the reservoir's state to any outputs, including agent actions or predictions. In this study, we find that reservoir computing greatly simplifies and speeds up reinforcement learning on memory tasks by (1) eliminating the need for backpropagation of gradients through time, (2) presenting all recent history simultaneously to the downstream network, and (3) performing many useful and generic nonlinear computations upstream from the trained modules. In particular, these findings offer significant benefit to meta-learning that depends primarily on efficient and highly general memory systems.