Recent progress in deep learning has relied on access to large and diverse datasets. Such data-driven progress has been less evident in offline reinforcement learning (RL), because offline RL data is usually collected to optimize specific target tasks limiting the data's diversity. In this work, we propose Exploratory data for Offline RL (ExORL), a data-centric approach to offline RL. ExORL first generates data with unsupervised reward-free exploration, then relabels this data with a downstream reward before training a policy with offline RL. We find that exploratory data allows vanilla off-policy RL algorithms, without any offline-specific modifications, to outperform or match state-of-the-art offline RL algorithms on downstream tasks. Our findings suggest that data generation is as important as algorithmic advances for offline RL and hence requires careful consideration from the community. Code and data can be found at https://github.com/denisyarats/exorl .
ANEO；Centre Borelli - ENS Paris-saclay（巴黎萨克雷高等师范学院博雷利中心）；Criteo AI Lab（科韬人工智能实验室）；Crest, ENSAE（法国国立统计与经济管理学院 Crest 研究中心）
The objective of offline RL is to learn optimal policies when a fixed exploratory demonstrations data-set is available and sampling additional observations is impossible (typically if this operation is either costly or rises ethical questions). In order to solve this problem, off the shelf approaches require a properly defined cost function (or its evaluation on the provided data-set), which are seldom available in practice. To circumvent this issue, a reasonable alternative is to query an expert for few optimal demonstrations in addition to the exploratory data-set. The objective is then to l…
Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap, because they involve large datasets collected by highly exploratory policies, and the trained policy is directly evaluated in the environment. In real-world situations, running a highly exploratory policy is prohibited to ensure system safety, the data is commonly very limited, and a trained policy should be well validated before deployment. In this paper, we …
Training large neural networks is known to be time-consuming, with the learning duration taking days or even weeks. To address this problem, large-batch optimization was introduced. This approach demonstrated that scaling mini-batch sizes with appropriate learning rate adjustments can speed up the training process by orders of magnitude. While long training time was not typically a major issue for model-free deep offline RL algorithms, recently introduced Q-ensemble methods achieving state-of-the-art performance made this issue more relevant, notably extending the training duration. In this wo…
Johannes Kepler University Linz（林茨约翰内斯·开普勒大学）；Institute of Advanced Research in Artificial Intelligence (IARAI)（人工智能高级研究所（IARAI））；Dynatrace Research（Dynatrace研究院）
The application of Reinforcement Learning (RL) in real world environments can be expensive or risky due to sub-optimal policies during training. In Offline RL, this problem is avoided since interactions with an environment are prohibited. Policies are learned from a given dataset, which solely determines their performance. Despite this fact, how dataset characteristics influence Offline RL algorithms is still hardly investigated. The dataset characteristics are determined by the behavioral policy that samples this dataset. Therefore, we define characteristics of behavioral policies as explorat…
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE（知识驱动的人机智能工程研究中心，教育部）；International Center of Future Science, Jilin University（未来科学国际中心，吉林大学）；JPMorgan AI Research（摩根大通AI研究）；Northwestern Polytechnical University（西北工业大学）；Lehigh University（莱斯大学）
Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare
School of Computer Science and Technology（计算机科学与技术学院）；University of Science and Technology of China（中国科学技术大学）；School of Data Science（数据科学学院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We consider a challenging theoretical problem in offline reinforcement learning (RL): obtaining sample-efficiency guarantees with a dataset lacking sufficient coverage, under only realizability-type assumptions for the function approximators. While the existing theory has addressed learning under realizability and under non-exploratory data separately, no work has been able to address both simultaneously (except for a concurrent work which we compare in detail). Under an additional gap assumption, we provide guarantees to a simple pessimistic algorithm based on a version space formed by margin…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
MDPs with low-rank transitions -- that is, the transition matrix can be factored into the product of two matrices, left and right -- is a highly representative structure that enables tractable learning. The left matrix enables expressive function approximation for value-based learning and has been studied extensively. In this work, we instead investigate sample-efficient learning with density features, i.e., the right matrix, which induce powerful models for state-occupancy distributions. This setting not only sheds light on leveraging unsupervised learning in RL, but also enables plug-in solu…
We provide a framework for accelerating reinforcement learning (RL) algorithms by heuristics constructed from domain knowledge or offline data. Tabula rasa RL algorithms require environment interactions or computation that scales with the horizon of the sequential decision-making task. Using our framework, we show how heuristic-guided RL induces a much shorter-horizon subproblem that provably solves the original task. Our framework can be viewed as a horizon-based regularization for controlling bias and variance in RL under a finite interaction budget. On the theoretical side, we characterize …
Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning
University of Maryland College Park（马里兰大学帕克分校）；University of Granada（格拉纳达大学）；Granada AI Lab（格拉纳达人工智能实验室）；DaSCI Andalusian Institute in Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所）；TECNALIA（TECNALIA 技术研究院）；Basque Research & Technology Alliance (BRTA)（巴斯克研究与技术联盟）；University of the Basque Country (UPV/EHU)（巴斯克大学）
Reinforcement learning (RL) algorithms hold the promise of enabling autonomous skill acquisition for robotic systems. However, in practice, real-world robotic RL typically requires time consuming data collection and frequent human intervention to reset the environment. Moreover, robotic policies learned with RL often fail when deployed beyond the carefully controlled setting in which they were learned. In this work, we study how these challenges can all be tackled by effective utilization of diverse offline datasets collected from previously seen tasks. When faced with a new task, our system a…
Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards
Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；Institute of Information Engineering, CAS（中国科学院信息工程研究所）；USTC（中国科学技术大学）；The Australian National University（澳大利亚国立大学）；Peking University（北京大学）；University of Macau（澳门大学）
Learning-based methods in robotics hold the promise of generalization, but what can be done if a learned policy does not generalize to a new situation? In principle, if an agent can at least evaluate its own success (i.e., with a reward classifier that generalizes well even when the policy does not), it could actively practice the task and finetune the policy in this situation. We study this problem in the setting of industrial insertion tasks, such as inserting connectors in sockets and setting screws. Existing algorithms rely on precise localization of the connector or socket and carefully m…
Data driven soft sensor design has recently gained immense popularity, due to advances in sensory devices, and a growing interest in data mining. While partial least squares (PLS) is traditionally used in the process literature for designing soft sensors, the statistical literature has focused on sparse learners, such as Lasso and relevance vector machine (RVM), to solve the high dimensional data problem. In the current study, predictive performances of three regression techniques, PLS, Lasso and RVM were assessed and compared under various offline and online soft sensing scenarios applied on …
We study policy gradient (PG) for reinforcement learning in continuous time and space under the regularized exploratory formulation developed by Wang et al. (2020). We represent the gradient of the value function with respect to a given parameterized stochastic policy as the expected integration of an auxiliary running reward function that can be evaluated using samples and the current value function. This effectively turns PG into a policy evaluation (PE) problem, enabling us to apply the martingale approach recently developed by Jia and Zhou (2021) for PE to solve our PG problem. Based on th…
Helsinki Institute for Information Technology（赫尔辛基信息技术研究所）；Helsinki University of Technology（赫尔辛基理工大学）
There is a wide variety of data mining methods available, and it is generally useful in exploratory data analysis to use many different methods for the same dataset. This, however, leads to the problem of whether the results found by one method are a reflection of the phenomenon shown by the results of another method, or whether the results depict in some sense unrelated properties of the data. For example, using clustering can give indication of a clear cluster structure, and computing correlations between variables can show that there are many significant correlations in the data. However, i…
NOVA Information Management School, Universidade Nova de Lisboa（里斯本新大学NOVA信息管理学院）
In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not always available, motivating research on regularization methods. In addition, current and past research have shown that simpler classification algorithms can reach state-of-the-art performance on computer vision tasks given a robust method to artificially augment the training dataset. Because of this, data augmentation techniques became a popular research t…
