ICML 2024 论文列表

To solve safety-critical decision-making problems, Inverse Constrained Reinforcement Learning (ICRL) infers constraints from expert demonstrations and seeks to imitate expert preference by utilizing these constraints. While prior ICRL research commonly overlooks the discrepancy between the training and deploying environments, we demonstrate that such a discrepancy can significantly compromise the reliability of the inferred constraints and thus induce unsafe movements. Motivated by this finding, we propose the Robust Constraint Inference (RCI) problem and an Adaptively Robust ICRL (AR-ICRL) algorithm to solve RCI efficiently. Specifically, we model the impact of misspecified dynamics with an opponent policy and learn a robust policy to facilitate safe control in a Markov Game. Subsequently, we adjust our constraint model to align the learned policies to expert demonstrations, accommodating both soft and hard optimality in our behavioral models. Empirical results demonstrate the significance of robust constraints and the effectiveness of the proposed AR-ICRL algorithm under continuous and discrete domains. The code is available at https://github.com/Jasonxu1225/AR-ICRL.

Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all currently known regret bounds allow for *error cancellations* --- one can compensate for a constraint violation in one round with a strict constraint satisfaction in another. This makes the online learning process unsafe since it only guarantees safety for the final (mixture) policy but not during learning. As Efroni et al. (2020) pointed out, it is an open question whether primal-dual algorithms can provably achieve sublinear regret if we do not allow error cancellations. In this paper, we give the first affirmative answer. We first generalize a result on last-iterate convergence of regularized primal-dual schemes to CMDPs with multiple constraints. Building upon this insight, we propose a model-based primal-dual algorithm to learn in an unknown CMDP. We prove that our algorithm achieves sublinear regret without error cancellations.

A wide range of (multivariate) temporal (1D) and spatial (2D) data analysis tasks, such as grouping vehicle sensor trajectories, can be formulated as clustering with given metric constraints. Existing metric-constrained clustering algorithms overlook the rich correlation between feature similarity and metric distance, i.e., metric autocorrelation. The model-based variations of these clustering algorithms (e.g. TICC and STICC) achieve SOTA performance, yet suffer from computational instability and complexity by using a metric-constrained Expectation-Maximization procedure. In order to address these two problems, we propose a novel clustering algorithm, MC-GTA (**M**odel-based **C**lustering via **G**oodness-of-fit **T**ests with **A**utocorrelations). Its objective is only composed of pairwise weighted sums of feature similarity terms (square Wasserstein-2 distance) and metric autocorrelation terms (a novel multivariate generalization of classic semivariogram). We show that MC-GTA is effectively minimizing the total hinge loss for intra-cluster observation pairs not passing goodness-of-fit tests, i.e., statistically not originating from the same distribution. Experiments on 1D/2D synthetic and real-world datasets demonstrate that MC-GTA successfully incorporates metric autocorrelation. It outperforms strong baselines by large margins (up to 14.3% in ARI and 32.1% in NMI) with faster and stabler optimization (>10x speedup).

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied during training because there might be model mismatch between the training and real environments. To address this challenge, we formulate the problem as constrained RL under model uncertainty, where the goal is to learn a policy that optimizes the reward and at the same time satisfies the constraint under model mismatch. We develop a Robust Constrained Policy Optimization (RCPO) algorithm, which is the first algorithm that applies to large/continuous state space and has theoretical guarantees on worst-case reward improvement and constraint violation at each iteration during the training. We show the effectiveness of our algorithm on a set of RL tasks with constraints.