ICML 2024 论文列表

The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging the Transformer architecture's scalability and the benefits of parameter sharing to exploit task similarities. However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance. In this work, we introduce the Harmony Multi-Task Decision Transformer (HarmoDT), a novel solution designed to identify an optimal harmony subspace of parameters for each task. We approach this as a bi-level optimization problem, employing a meta-learning framework that leverages gradient-based techniques. The upper level of this framework is dedicated to learning a task-specific mask that delineates the harmony subspace, while the inner level focuses on updating parameters to enhance the overall performance of the unified policy. Empirical evaluations on a series of benchmarks demonstrate the superiority of HarmoDT, verifying the effectiveness of our approach.

This paper addresses a policy optimization task with the conditional value-at-risk (CVaR) objective. We introduce the *predictive CVaR policy gradient*, a novel approach that seamlessly integrates risk-neutral policy gradient algorithms with minimal modifications. Our method incorporates a reweighting strategy in gradient calculation -- individual cost terms are reweighted in proportion to their *predicted* contribution to the objective. These weights can be easily estimated through a separate learning procedure. We provide theoretical and empirical analyses, demonstrating the validity and effectiveness of our proposed method.

*Inverse reinforcement learning* (IRL) aims to recover the reward function of an *expert* agent from demonstrations of behavior. It is well-known that the IRL problem is fundamentally ill-posed, i.e., many reward functions can explain the demonstrations. For this reason, IRL has been recently reframed in terms of estimating the *feasible reward set* (Metelli et al., 2021), thus, postponing the selection of a single reward. However, so far, the available formulations and algorithmic solutions have been proposed and analyzed mainly for the *online* setting, where the learner can interact with the environment and query the expert at will. This is clearly unrealistic in most practical applications, where the availability of an *offline* dataset is a much more common scenario. In this paper, we introduce a novel notion of feasible reward set capturing the opportunities and limitations of the offline setting and we analyze the complexity of its estimation. This requires the introduction an original learning framework that copes with the intrinsic difficulty of the setting, for which data coverage is not under control. Then, we propose two computationally and statistically efficient algorithms, IRLO and PIRLO, for addressing the problem. In particular, the latter adopts a specific form of *pessimism* to enforce the novel, desirable property of *inclusion monotonicity* of the delivered feasible set. With this work, we aim to provide a panorama of the challenges of the offline IRL problem and how they can be fruitfully addressed.

Recently, deep reinforcement learning has shown promising results for learning fast heuristics to solve routing problems. Meanwhile, most of the solvers suffer from generalizing to an unseen distribution or distributions with different scales. To address this issue, we propose a novel architecture, called Invariant Nested View Transformer (INViT), which is designed to enforce a nested design together with invariant views inside the encoders to promote the generalizability of the learned solver. It applies a modified policy gradient algorithm enhanced with data augmentations. We demonstrate that the proposed INViT achieves a dominant generalization performance on both TSP and CVRP problems with various distributions and different problem scales. Our source code and datasets are available in supplementary materials.

Online linear programming plays an important role in both revenue management and resource allocation, and recent research has focused on developing efficient first-order online learning algorithms. Despite the empirical success of first-order methods, they typically achieve regret no better than $\mathcal{O}(\sqrt{T})$, which is suboptimal compared to the $\mathcal{O}(\log T)$ result guaranteed by the state-of-the-art linear programming (LP)-based online algorithms. This paper establishes several important facts about online linear programming, which unveils the challenge for first-order online algorithms to achieve beyond $\mathcal{O}(\sqrt{T})$ regret. To address this challenge, we introduce a new algorithmic framework which decouples learning from decision-making. For the first time, we show that first-order methods can achieve regret $\mathcal{O}(T^{1/3})$ with this new framework.

Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL) problem and introduces an innovative actor-critic algorithm named MOAC which finds a policy by iteratively making trade-offs among conflicting reward signals. Notably, we provide the first analysis of finite-time Pareto-stationary convergence and corresponding sample complexity in both discounted and average reward settings. Our approach has two salient features: (a) MOAC mitigates the cumulative estimation bias resulting from finding an optimal common gradient descent direction out of stochastic samples. This enables provable convergence rate and sample complexity guarantees independent of the number of objectives; (b) With proper momentum coefficient, MOAC initializes the weights of individual policy gradients using samples from the environment, instead of manual initialization. This enhances the practicality and robustness of our algorithm. Finally, experiments conducted on a real-world dataset validate the effectiveness of our proposed method.

Despite the recent advancements in offline RL, no unified algorithm could achieve superior performance across a broad range of tasks. Offline *value function learning*, in particular, struggles with sparse-reward, long-horizon tasks due to the difficulty of solving credit assignment and extrapolation errors that accumulates as the horizon of the task grows. On the other hand, models that can perform well in long-horizon tasks are designed specifically for goal-conditioned tasks, which commonly perform worse than value function learning methods on short-horizon, dense-reward scenarios. To bridge this gap, we propose a hierarchical planner designed for offline RL called PlanDQ. PlanDQ incorporates a diffusion-based planner at the high level, named D-Conductor, which guides the low-level policy through sub-goals. At the low level, we used a Q-learning based approach called the Q-Performer to accomplish these sub-goals. Our experimental results suggest that PlanDQ can achieve superior or competitive performance on D4RL continuous control benchmark tasks as well as AntMaze, Kitchen, and Calvin as long-horizon tasks.

Proteins are complex molecules responsible for different functions in nature. Enhancing the functionality of proteins and cellular fitness can significantly impact various industries. However, protein optimization using computational methods remains challenging, especially when starting from low-fitness sequences. We propose LatProtRL, an optimization method to efficiently traverse a latent space learned by an encoder-decoder leveraging a large protein language model. To escape local optima, our optimization is modeled as a Markov decision process using reinforcement learning acting directly in latent space. We evaluate our approach on two important fitness optimization tasks, demonstrating its ability to achieve comparable or superior fitness over baseline methods. Our findings and in vitro evaluation show that the generated sequences can reach high-fitness regions, suggesting a substantial potential of LatProtRL in lab-in-the-loop scenarios.

In the realm of reinforcement learning (RL), accounting for risk is crucial for making decisions under uncertainty, particularly in applications where safety and reliability are paramount. In this paper, we introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-DisRL), with static Lipschitz Risk Measures (LRM) and general function approximation. Our framework covers a broad class of risk-sensitive RL, and facilitates analysis of the impact of estimation functions on the effectiveness of RSRL strategies and evaluation of their sample complexity. We design two innovative meta-algorithms: RS-DisRL-M, a model-based strategy for model-based function approximation, and RS-DisRL-V, a model-free approach for general value function approximation. With our novel estimation techniques via Least Squares Regression (LSR) and Maximum Likelihood Estimation (MLE) in distributional RL with augmented Markov Decision Process (MDP), we derive the first $\widetilde{\mathcal{O}}(\sqrt{K})$ dependency of the regret upper bound for RSRL with static LRM, marking a pioneering contribution towards statistically efficient algorithms in this domain.

Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distributions, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines the strengths of deep learning with CMEs in order to address these challenges. Specifically, our approach leverages the end-to-end neural network (NN) optimization framework using a kernel-based objective. This design circumvents the computationally expensive Gram matrix inversion required by current CME methods. To further enhance performance, we provide efficient strategies to optimize the remaining kernel hyperparameters. In conditional density estimation tasks, our NN-CME hybrid achieves competitive performance and often surpasses existing deep learning-based methods. Lastly, we showcase its remarkable versatility by seamlessly integrating it into reinforcement learning (RL) contexts. Building on Q-learning, our approach naturally leads to a new variant of distributional RL methods, which demonstrates consistent effectiveness across different environments.

In preference-based Reinforcement Learning (RL), obtaining a large number of preference labels are both time-consuming and costly. Furthermore, the queried human preferences cannot be utilized for the new tasks. In this paper, we propose Zero-shot Cross-task Preference Alignment and Robust Reward Learning (PEARL), which learns policies from cross-task preference transfer without any human labels of the target task. Our contributions include two novel components that facilitate the transfer and learning process. The first is Cross-task Preference Alignment (CPA), which transfers the preferences between tasks via optimal transport. The key idea of CPA is to use Gromov-Wasserstein distance to align the trajectories between tasks, and the solved optimal transport matrix serves as the correspondence between trajectories. The target task preferences are computed as the weighted sum of source task preference labels with the correspondence as weights. Moreover, to ensure robust learning from these transferred labels, we introduce Robust Reward Learning (RRL), which considers both reward mean and uncertainty by modeling rewards as Gaussian distributions. Empirical results on robotic manipulation tasks from Meta-World and Robomimic demonstrate that our method is capable of transferring preference labels across tasks accurately and then learns well-behaved policies. Notably, our approach significantly exceeds existing methods when there are few human preferences. The code and videos of our method are available at: https://sites.google.com/view/pearl-preference.

In the emergency department (ED), patients undergo triage and multiple laboratory tests before diagnosis. This time-consuming process causes ED crowding which impacts patient mortality, medical errors, staff burnout, etc. This work proposes (time) *cost-effective diagnostic assistance* that leverages artificial intelligence systems to help ED clinicians make efficient and accurate diagnoses. In collaboration with ED clinicians, we use public patient data to curate MIMIC-ED-Assist, a benchmark for AI systems to suggest laboratory tests that minimize wait time while accurately predicting critical outcomes such as death. With MIMIC-ED-Assist, we develop ED-Copilot which sequentially suggests patient-specific laboratory tests and makes diagnostic predictions. ED-Copilot employs a pre-trained bio-medical language model to encode patient information and uses reinforcement learning to minimize ED wait time and maximize prediction accuracy. On MIMIC-ED-Assist, ED-Copilot improves prediction accuracy over baselines while halving average wait time from four hours to two hours. ED-Copilot can also effectively personalize treatment recommendations based on patient severity, further highlighting its potential as a diagnostic assistant. Since MIMIC-ED-Assist is a retrospective benchmark, ED-Copilot is restricted to recommend only observed tests. We show ED-Copilot achieves competitive performance without this restriction as the maximum allowed time increases. Our code is available at https://github.com/cxcscmu/ED-Copilot.

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with visual observations, but previous methods cannot refine the structured states with rewards due to a lack of efficiency. Accessibility also remains an issue, as extensive domain knowledge is required to interpret symbolic policies. In this paper, we present a neuro-symbolic framework for jointly learning structured states and symbolic policies, whose key idea is to distill the vision foundation model into an efficient perception module and refine it during policy learning. Moreover, we design a pipeline to prompt GPT-4 to generate textual explanations for the learned policies and decisions, significantly reducing users' cognitive load to understand the symbolic policies. We verify the efficacy of our approach on nine Atari tasks and present GPT-generated explanations for policies and decisions.

In classic Reinforcement Learning (RL), the agent maximizes an additive objective of the visited states, e.g., a value function. Unfortunately, objectives of this type cannot model many real-world applications such as experiment design, exploration, imitation learning, and risk-averse RL to name a few. This is due to the fact that additive objectives disregard interactions between states that are crucial for certain tasks. To tackle this problem, we introduce *Global* RL (GRL), where rewards are *globally* defined over trajectories instead of *locally* over states. Global rewards can capture *negative interactions* among states, e.g., in exploration, via submodularity, *positive interactions*, e.g., synergetic effects, via supermodularity, while mixed interactions via combinations of them. By exploiting ideas from submodular optimization, we propose a novel algorithmic scheme that converts any GRL problem to a sequence of classic RL problems and solves it efficiently with curvature-dependent approximation guarantees. We also provide hardness of approximation results and empirically demonstrate the effectiveness of our method on several GRL instances.

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel *Auxiliary-Delayed Reinforcement Learning (AD-RL)* method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.