Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In this paper, we propose a novel framework for IRL-based IL that prioritizes task alignment over conventional data alignment. Our framework is a semi-supervised approach that leverages expert demonstrations as weak supervision to derive a set of candidate reward functions that align with the task rather than only with the data. It then adopts an adversarial mechanism to train a policy with this set of reward functions to gain a collective validation of the policy's ability to accomplish the task. We provide theoretical insights into this framework's ability to mitigate task-reward misalignment and present a practical implementation. Our experimental results show that our framework outperforms conventional IL baselines in complex and transfer learning scenarios.

HyQE: Ranking Contexts with Hypothetical Query Embeddings

In retrieval-augmented systems, context ranking techniques are commonly employed to reorder the retrieved contexts based on their relevance to a user query. A standard approach is to measure this relevance through the similarity between contexts and queries in the embedding space. However, such similarity often fails to capture the relevance. Alternatively, large language models (LLMs) have been used for ranking contexts. However, they can encounter scalability issues when the number of candidate contexts grows and the context window sizes of the LLMs remain constrained. Additionally, these approaches require fine-tuning LLMs with domain-specific data. In this work, we introduce a scalable ranking framework that combines embedding similarity and LLM capabilities without requiring LLM fine-tuning. Our framework uses a pre-trained LLM to hypothesize the user query based on the retrieved contexts and ranks the context based on the similarity between the hypothesized queries and the user query. Our framework is efficient at inference time and is compatible with many other retrieval and ranking techniques. Experimental results show that our method improves the ranking performance across multiple benchmarks. The complete code and data are available at https://github.com/zwc662/hyqe

Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems

Optimal control methods provide solutions to safety-critical problems but easily become intractable. Control Barrier Functions (CBFs) have emerged as a popular technique that facilitates their solution by provably guaranteeing safety, through their forward invariance property, at the expense of some performance loss. This approach involves defining a performance objective alongside CBF-based safety constraints that must always be enforced. Unfortunately, both performance and solution feasibility can be significantly impacted by two key factors: (i) the selection of the cost function and associated parameters, and (ii) the calibration of parameters within the CBF-based constraints, which capture the trade-off between performance and conservativeness. %as well as infeasibility. To address these challenges, we propose a Reinforcement Learning (RL)-based Receding Horizon Control (RHC) approach leveraging Model Predictive Control (MPC) with CBFs (MPC-CBF). In particular, we parameterize our controller and use bilevel optimization, where RL is used to learn the optimal parameters while MPC computes the optimal control input. We validate our method by applying it to the challenging automated merging control problem for Connected and Automated Vehicles (CAVs) at conflicting roadways. Results demonstrate improved performance and a significant reduction in the number of infeasible cases compared to traditional heuristic approaches used for tuning CBF-based controllers, showcasing the effectiveness of the proposed method.

Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning

Offline safe reinforcement learning (RL) aims to train a constraint satisfaction policy from a fixed dataset. Current state-of-the-art approaches are based on supervised learning with a conditioned policy. However, these approaches fall short in real-world applications that involve complex tasks with rich temporal and logical structures. In this paper, we propose temporal logic Specification-conditioned Decision Transformer (SDT), a novel framework that harnesses the expressive power of signal temporal logic (STL) to specify complex temporal rules that an agent should follow and the sequential modeling capability of Decision Transformer (DT). Empirical evaluations on the DSRL benchmarks demonstrate the better capacity of SDT in learning safe and high-reward policies compared with existing approaches. In addition, SDT shows good alignment with respect to different desired degrees of satisfaction of the STL specification that it is conditioned on.

DeLF: Designing Learning Environments with Foundation Models

Reinforcement learning (RL) offers a capable and intuitive structure for the fundamental sequential decision-making problem. Despite impressive breakthroughs, it can still be difficult to employ RL in practice in many simple applications. In this paper, we try to address this issue by introducing a method for designing the components of the RL environment for a given, user-intended application. We provide an initial formalization for the problem of RL component design, that concentrates on designing a good representation for observation and action space. We propose a method named DeLF: Designing Learning Environments with Foundation Models, that employs large language models to design and codify the user's intended learning scenario. By testing our method on four different learning environments, we demonstrate that DeLF can obtain executable environment codes for the corresponding RL problems.

Zero-Shot Enhancement of Low-Light Image Based on Retinex Decomposition

Two difficulties here make low-light image enhancement a challenging task; firstly, it needs to consider not only luminance restoration but also image contrast, image denoising and color distortion issues simultaneously. Second, the effectiveness of existing low-light enhancement methods depends on paired or unpaired training data with poor generalization performance. To solve these difficult problems, we propose in this paper a new learning-based Retinex decomposition of zero-shot low-light enhancement method, called ZERRINNet. To this end, we first designed the N-Net network, together with the noise loss term, to be used for denoising the original low-light image by estimating the noise of the low-light image. Moreover, RI-Net is used to estimate the reflection component and illumination component, and in order to solve the color distortion and contrast, we use the texture loss term and segmented smoothing loss to constrain the reflection component and illumination component. Finally, our method is a zero-reference enhancement method that is not affected by the training data of paired and unpaired datasets, so our generalization performance is greatly improved, and in the paper, we have effectively validated it with a homemade real-life low-light dataset and additionally with advanced vision tasks, such as face detection, target recognition, and instance segmentation. We conducted comparative experiments on a large number of public datasets and the results show that the performance of our method is competitive compared to the current state-of-the-art methods. The code is available at:https://github.com/liwenchao0615/ZERRINNet

OVLA: Neural Network Ownership Verification using Latent Watermarks

Ownership verification for neural networks is important for protecting these models from illegal copying, free-riding, re-distribution and other intellectual property misuse. We present a novel methodology for neural network ownership verification based on the notion of latent watermarks. Existing ownership verification methods either modify or introduce constraints to the neural network parameters, which are accessible to an attacker in a white-box attack and can be harmful to the network's normal operation, or train the network to respond to specific watermarks in the inputs similar to data poisoning-based backdoor attacks, which are susceptible to backdoor removal techniques. In this paper, we address these problems by decoupling a network's normal operation from its responses to watermarked inputs during ownership verification. The key idea is to train the network such that the watermarks remain dormant unless the owner's secret key is applied to activate it. The secret key is realized as a specific perturbation only known to the owner to the network's parameters. We show that our approach offers strong defense against backdoor detection, backdoor removal and surrogate model attacks.In addition, our method provides protection against ambiguity attacks where the attacker either tries to guess the secret weight key or uses fine-tuning to embed their own watermarks with a different key into a pre-trained neural network. Experimental results demonstrate the advantages and effectiveness of our proposed approach.

Trust-Aware Resilient Control and Coordination of Connected and Automated Vehicles

We address the security of a network of Connected and Automated Vehicles (CAVs) cooperating to navigate through a conflict area. Adversarial attacks such as Sybil attacks can cause safety violations resulting in collisions and traffic jams. In addition, uncooperative (but not necessarily adversarial) CAVs can also induce similar adversarial effects on the traffic network. We propose a decentralized resilient control and coordination scheme that mitigates the effects of adversarial attacks and uncooperative CAVs by utilizing a trust framework. Our trust-aware scheme can guarantee safe collision free coordination and mitigate traffic jams. Simulation results validate the theoretical guarantee of our proposed scheme, and demonstrate that it can effectively mitigate adversarial effects across different traffic scenarios.

PAGAR: Imitation Learning with Protagonist Antagonist Guided Adversarial Reward

Imitation learning (IL) algorithms often rely on inverse reinforcement learning (IRL) to first learn a reward function from expert demonstrations. However, IRL can suffer from identifiability issues and there is no performance or efficiency guarantee when training with the learned reward function. In this paper, we propose Protagonist Antagonist Guided Adversarial Reward (PAGAR), a semi-supervised learning paradigm for designing rewards for policy training. PAGAR employs an iterative adversarially search for reward functions to maximize the performance gap between a protagonist policy and an antagonist policy. This allows the protagonist policy to perform well across a set of possible reward functions despite the identifiability issue. When integrated with IRL-based IL, PAGAR guarantees that the trained policy succeeds in the underlying task. Furthermore, we introduce a practical on-and-off policy approach to IL with PAGAR. This approach maximally utilizes samples from both the protagonist and antagonist policies for the optimization of policy and reward functions. Experimental results demonstrate that our algorithm achieves higher training efficiency compared to state-of-the-art IL/IRL baselines in standard settings, as well as zero-shot learning from demonstrations in transfer environments.

Optimal Control of Connected Automated Vehicles with Event-Triggered Control Barrier Functions: a Test Bed for Safe Optimal Merging

We address the problem of controlling Connected and Automated Vehicles (CAVs) in conflict areas of a traffic network subject to hard safety constraints. It has been shown that such problems can be solved through a combination of tractable optimal control problems and Control Barrier Functions (CBFs) that guarantee the satisfaction of all constraints. These solutions can be reduced to a sequence of Quadratic Programs (QPs) which are efficiently solved on line over discrete time steps. However, guaranteeing the feasibility of the CBF-based QP method within each discretized time interval requires the careful selection of time steps which need to be sufficiently small. This creates computational requirements and communication rates between agents which may hinder the controller's application to real CAVs. In this paper, we overcome this limitation by adopting an event-triggered approach for CAVs in a conflict area such that the next QP is triggered by properly defined events with a safety guarantee. We present a laboratory-scale test bed we have developed to emulate merging roadways using mobile robots as CAVs which can be used to demonstrate how the event-triggered scheme is computationally efficient and can handle measurement uncertainties and noise compared to time-driven control while guaranteeing safety.