Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget

In this paper, we introduce the constrained best mixed arm identification (CBMAI) problem with a fixed budget. This is a pure exploration problem in a stochastic finite armed bandit model. Each arm is associated with a reward and multiple types of costs from unknown distributions. Unlike the unconstrained best arm identification problem, the optimal solution for the CBMAI problem may be a randomized mixture of multiple arms. The goal thus is to find the best mixed arm that maximizes the expected reward subject to constraints on the expected costs with a given learning budget $N$. We propose a novel, parameter-free algorithm, called the Score Function-based Successive Reject (SFSR) algorithm, that combines the classical successive reject framework with a novel score-function-based rejection criteria based on linear programming theory to identify the optimal support. We provide a theoretical upper bound on the mis-identification (of the the support of the best mixed arm) probability and show that it decays exponentially in the budget $N$ and some constants that characterize the hardness of the problem instance. We also develop an information theoretic lower bound on the error probability that shows that these constants appropriately characterize the problem difficulty. We validate this empirically on a number of average and hard instances.

Sparse but Strong: Crafting Adversarially Robust Graph Lottery Tickets

Graph Lottery Tickets (GLTs), comprising a sparse adjacency matrix and a sparse graph neural network (GNN), can significantly reduce the inference latency and compute footprint compared to their dense counterparts. Despite these benefits, their performance against adversarial structure perturbations remains to be fully explored. In this work, we first investigate the resilience of GLTs against different structure perturbation attacks and observe that they are highly vulnerable and show a large drop in classification accuracy. Based on this observation, we then present an adversarially robust graph sparsification (ARGS) framework that prunes the adjacency matrix and the GNN weights by optimizing a novel loss function capturing the graph homophily property and information associated with both the true labels of the train nodes and the pseudo labels of the test nodes. By iteratively applying ARGS to prune both the perturbed graph adjacency matrix and the GNN model weights, we can find adversarially robust graph lottery tickets that are highly sparse yet achieve competitive performance under different untargeted training-time structure attacks. Evaluations conducted on various benchmarks, considering different poisoning structure attacks, namely, PGD, MetaAttack, Meta-PGD, and PR-BCD demonstrate that the GLTs generated by ARGS can significantly improve the robustness, even when subjected to high levels of sparsity.

Regret Analysis of the Posterior Sampling-based Learning Algorithm for Episodic POMDPs

Compared to Markov Decision Processes (MDPs), learning in Partially Observable Markov Decision Processes (POMDPs) can be significantly harder due to the difficulty of interpreting observations. In this paper, we consider episodic learning problems in POMDPs with unknown transition and observation models. We consider the Posterior Sampling-based Reinforcement Learning (PSRL) algorithm for POMDPs and show that its Bayesian regret scales as the square root of the number of episodes. In general, the regret scales exponentially with the horizon length $H$, and we show that this is inevitable by providing a lower bound. However, under the condition that the POMDP is undercomplete and weakly revealing, we establish a polynomial Bayesian regret bound that improves the regret bound by a factor of $\Omega(H^2\sqrt{SA})$ over the recent result by arXiv:2204.08967.

Correct-by-Construction Design of Contextual Robotic Missions Using Contracts

Effectively specifying and implementing robotic missions pose a set of challenges to software engineering for robotic systems, since they require formalizing and executing a robot's high-level tasks while considering various application scenarios and conditions, also known as contexts, in real-world operational environments. Writing correct mission specifications that explicitly account for multiple contexts can be a tedious and error-prone task. Moreover, as the number of context, hence the specification, becomes more complex, generating a correct-by-construction implementation, e.g., by using synthesis methods, can become intractable. A viable approach to address these issues is to decompose the mission specification into smaller sub-missions, with each sub-mission corresponding to a specific context. However, such a compositional approach would still pose challenges in ensuring the overall mission correctness. In this paper, we propose a new, compositional framework for the specification and implementation of contextual robotic missions using assume-guarantee contracts. The mission specification is captured in a hierarchical and modular way and each sub-mission is synthesized as a robot controller. We address the problem of dynamically switching between sub-mission controllers while ensuring correctness under certain conditions.

Optimal Control of Logically Constrained Partially Observable and Multi-Agent Markov Decision Processes

Autonomous systems often have logical constraints arising, for example, from safety, operational, or regulatory requirements. Such constraints can be expressed using temporal logic specifications. The system state is often partially observable. Moreover, it could encompass a team of multiple agents with a common objective but disparate information structures and constraints. In this paper, we first introduce an optimal control theory for partially observable Markov decision processes (POMDPs) with finite linear temporal logic constraints. We provide a structured methodology for synthesizing policies that maximize a cumulative reward while ensuring that the probability of satisfying a temporal logic constraint is sufficiently high. Our approach comes with guarantees on approximate reward optimality and constraint satisfaction. We then build on this approach to design an optimal control framework for logically constrained multi-agent settings with information asymmetry. We illustrate the effectiveness of our approach by implementing it on several case studies.

Exact and Cost-Effective Automated Transformation of Neural Network Controllers to Decision Tree Controllers

Over the past decade, neural network (NN)-based controllers have demonstrated remarkable efficacy in a variety of decision-making tasks. However, their black-box nature and the risk of unexpected behaviors and surprising results pose a challenge to their deployment in real-world systems with strong guarantees of correctness and safety. We address these limitations by investigating the transformation of NN-based controllers into equivalent soft decision tree (SDT)-based controllers and its impact on verifiability. Differently from previous approaches, we focus on discrete-output NN controllers including rectified linear unit (ReLU) activation functions as well as argmax operations. We then devise an exact but cost-effective transformation algorithm, in that it can automatically prune redundant branches. We evaluate our approach using two benchmarks from the OpenAI Gym environment. Our results indicate that the SDT transformation can benefit formal verification, showing runtime improvements of up to 21x and 2x for MountainCar-v0 and CartPole-v0, respectively.

Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation

Constrained Markov decision processes (CMDPs) model scenarios of sequential decision making with multiple objectives that are increasingly important in many applications. However, the model is often unknown and must be learned online while still ensuring the constraint is met, or at least the violation is bounded with time. Some recent papers have made progress on this very challenging problem but either need unsatisfactory assumptions such as knowledge of a safe policy, or have high cumulative regret. We propose the Safe PSRL (posterior sampling-based RL) algorithm that does not need such assumptions and yet performs very well, both in terms of theoretical regret bounds as well as empirically. The algorithm achieves an efficient tradeoff between exploration and exploitation by use of the posterior sampling principle, and provably suffers only bounded constraint violation by leveraging the idea of pessimism. Our approach is based on a primal-dual approach. We establish a sub-linear $\tilde{\mathcal{ O}}\left(H^{2.5} \sqrt{|\mathcal{S}|^2 |\mathcal{A}| K} \right)$ upper bound on the Bayesian reward objective regret along with a bounded, i.e., $\tilde{\mathcal{O}}\left(1\right)$ constraint violation regret over $K$ episodes for an $|\mathcal{S}|$-state, $|\mathcal{A}|$-action and horizon $H$ CMDP.

Contract-Based Specification Refinement and Repair for Mission Planning

We address the problem of modeling, refining, and repairing formal specifications for robotic missions using assume-guarantee contracts. We show how to model mission specifications at various levels of abstraction and implement them using a library of pre-implemented specifications. Suppose the specification cannot be met using components from the library. In that case, we compute a proxy for the best approximation to the specification that can be generated using elements from the library. Afterward, we propose a systematic way to either 1) search for and refine the `missing part' of the specification that the library cannot meet or 2) repair the current specification such that the existing library can refine it. Our methodology for searching and repairing mission requirements leverages the quotient, separation, composition, and merging operations between contracts.

ReIGNN: State Register Identification Using Graph Neural Networks for Circuit Reverse Engineering

Reverse engineering an integrated circuit netlist is a powerful tool to help detect malicious logic and counteract design piracy. A critical challenge in this domain is the correct classification of data-path and control-logic registers in a design. We present ReIGNN, a novel learning-based register classification methodology that combines graph neural networks (GNNs) with structural analysis to classify the registers in a circuit with high accuracy and generalize well across different designs. GNNs are particularly effective in processing circuit netlists in terms of graphs and leveraging properties of the nodes and their neighborhoods to learn to efficiently discriminate between different types of nodes. Structural analysis can further rectify any registers misclassified as state registers by the GNN by analyzing strongly connected components in the netlist graph. Numerical results on a set of benchmarks show that ReIGNN can achieve, on average, 96.5% balanced accuracy and 97.7% sensitivity across different designs.

Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications

We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL) specification. We propose a method to effectively augment the MDP state space to capture the required state history and express the STL objective as a reachability objective. The planning problem can then be formulated as a finite-horizon constrained Markov decision process (CMDP). For a general finite horizon CMDP problem with unknown transition probability, we develop a reinforcement learning scheme that can leverage any model-free RL algorithm to provide an approximately optimal policy out of the general space of non-stationary randomized policies. We illustrate the effectiveness of our approach in the context of robotic motion planning for complex missions under uncertainty and performance objectives.