Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with long-horizon tasks due to the high compounding error of auto-regressive models. To overcome this limitation, we go beyond next-token prediction and introduce Planning Tokens, which contain high-level, long time-scale information about the agent's future. Predicting dual time-scale tokens at regular intervals enables our model to use these long-horizon Planning Tokens as a form of implicit planning to guide its low-level policy and reduce compounding error. This architectural modification significantly enhances performance on long-horizon tasks, establishing a new state-of-the-art in complex D4RL environments. Additionally, we demonstrate that Planning Tokens improve the interpretability of the model's policy through the interpretable plan visualisations and attention map.
Offline reinforcement learning (RL) provides a framework for learning decision-making from offline data and therefore constitutes a promising approach for real-world applications as automated driving. Self-driving vehicles (SDV) learn a policy, which potentially even outperforms the behavior in the sub-optimal data set. Especially in safety-critical applications as automated driving, explainability and transferability are key to success. This motivates the use of model-based offline RL approaches, which leverage planning. However, current state-of-the-art methods often neglect the influence of…
GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models
University of Warwick（华威大学）；Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）；University of Cambridge（剑桥大学）；University of Liverpool（利物浦大学）
Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；JD iCity & JD Intelligent Cities Research, JD Technology（京东科技京东城市与京东智能城市研究院）
The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without environment interaction. Unfortunately, existing offline RL methods still face many practical challenges in real-world system control tasks, such as computational restriction during agent training and the requirement of extra control flexibility. The model-based planning framework provides an attractive alternative. However, most model-based planning algorithms are not designed for offline settings. Simply combining …
Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a system's operation, but no direct access to the system when learning a policy. Recent work on training RL policies from offline data has shown results both with model-free policies learned directly from the data, or with planning on top of learnt models of the data. Model-free policies tend to be more performant, but are more opaque, harder to command externally, and less easy to integrate into larger systems. We propose an offline learner that …
Planning in stochastic and partially observable environments is a central issue in artificial intelligence. One commonly used technique for solving such a problem is by constructing an accurate model firstly. Although some recent approaches have been proposed for learning optimal behaviour under model uncertainty, prior knowledge about the environment is still needed to guarantee the performance of the proposed algorithms. With the benefits of the Predictive State Representations~(PSRs) approach for state representation and model prediction, in this paper, we introduce an approach for planning…
Learning efficiently from small amounts of data has long been the focus of model-based reinforcement learning, both for the online case when interacting with the environment and the offline case when learning from a fixed dataset. However, to date no single unified algorithm could demonstrate state-of-the-art results in both settings. In this work, we describe the Reanalyse algorithm which uses model-based policy and value improvement operators to compute new improved training targets on existing data points, allowing efficient learning for data budgets varying by several orders of magnitude. …
Intel Labs（英特尔实验室）；Technion Israel Institute of Technology（以色列理工学院）
Offline reinforcement-learning (RL) algorithms learn to make decisions using a given, fixed training dataset without online data collection. This problem setting is captivating because it holds the promise of utilizing previously collected datasets without any costly or risky interaction with the environment. However, this promise also bears the drawback of this setting as the restricted dataset induces uncertainty because the agent can encounter unfamiliar sequences of states and actions that the training data did not cover. To mitigate the destructive uncertainty effects, we need to balance …
ANITI - Artificial and Natural Intelligence Toulouse Institute（图卢兹人工智能与自然智能研究所）；Université de Toulouse（图卢兹大学）；ISAE-SUPAERO（法国国立高等航空航天学院）
The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning from the control of unmanned vehicles to human-robot interaction and medical applications are accessible on the internet. With the intention of limiting the costs of the learning procedure it is convenient to exploit the information that is already available rather than collecting new data. Nevertheless, the incapability to augment the batch can lead the autono…
Massachusetts Institute of Technology（麻省理工学院）；University of California, Berkeley（加州大学伯克利分校）
Motivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce and solve a general class of non-stationary multi-armed bandit problems that have the following two features: (i) the decision maker can pull and collect rewards from up to $K\,(\ge 1)$ out of $N$ different arms in each time period; (ii) the expected reward of an arm immediately drops after it is pulled, and then non-parametrically recovers as the arm's idle time increases. With the objective of maximizing the expected cumulative reward over $T$ time periods, we design a class of …
Indian Institute of Technology Madras（马德拉斯印度理工学院）；Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
UC Santa Barbara（加州大学圣巴巴拉分校）；Salesforce Research（赛富时研究院）
The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications. Existing work on OPE mostly focus on evaluating a fixed target policy $π$, which does not provide useful bounds for offline policy learning as $π$ will then be data-dependent. We address this problem by simultaneously evaluating all policies in a policy class $Π$ -- uniform convergence in OPE -- and obtain nearly optimal error bounds for a number of global / local policy classes. Our results imply that the model-based planning achieves an optimal episo…
Adaptive Science Operations in Deep Space Missions Using Offline Belief State Planning
Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, 94305, USA（斯坦福大学航空航天系）；Intelligent Systems Division, NASA Ames Research Center, Moffett Field, CA, 94035, USA（美国航空航天局阿姆斯研究中心智能系统分部）
Shanghai Jiaotong University（上海交通大学）；JD Explore Academy（京东探索研究院）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Sydney（悉尼大学）
Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment. Recently, offline RL has been viewed as a sequence modeling problem, where an agent generates a sequence of subsequent actions based on a set of static transition experiences. However, existing approaches that use transformers to attend to all tokens naively can overlook the dependencies between different tokens and limit long-term dependency learning. In this paper, we propose the Graph Decision Transformer (GDT), a novel offline…
Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation error for actions outside the dataset. In this paper, we adopt a different framework, which learns the V-function instead of the Q-function to naturally keep the learning procedure within the support of an offline dataset. To enable effective generalization while maintaining proper conservatism in offline learning, we propose Expectile V-Learning (EVL), which sm…
University of California, Berkeley（加州大学伯克利分校）；University of Illinois, Chicago（伊利诺伊大学芝加哥分校）
Our team is proposing to run a full-scale energy demand response experiment in an office building. Although this is an exciting endeavor which will provide value to the community, collecting training data for the reinforcement learning agent is costly and will be limited. In this work, we examine how offline training can be leveraged to minimize data costs (accelerate convergence) and program implementation costs. We present two approaches to doing so: pretraining our model to warm start the experiment with simulated tasks, and using a planning model trained to simulate the real world's reward…
Siemens Technology（西门子技术部）；Technical University of Munich（慕尼黑工业大学）
Offline reinforcement learning (RL) Algorithms are often designed with environments such as MuJoCo in mind, in which the planning horizon is extremely long and no noise exists. We compare model-free, model-based, as well as hybrid offline RL approaches on various industrial benchmark (IB) datasets to test the algorithms in settings closer to real world problems, including complex noise and partially observable states. We find that on the IB, hybrid approaches face severe difficulties and that simpler algorithms, such as rollout based algorithms or model-free algorithms with simpler regularizer…
Shanghai Jiao Tong University（上海交通大学）；Microsoft Research Asia（微软亚洲研究院）
Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic sequence generation problem, adopting sequence models such as Transformer architecture to model distributions over trajectories, and repurposing beam search as a planning algorithm. However, the training datasets utilized in general offline RL tasks are quite limited and often suffer from insufficient distribution coverage, which could be harmful to training seque…
In this paper we propose a Deep Reinforcement Learning approach to solve a multimodal transportation planning problem, in which containers must be assigned to a truck or to trains that will transport them to their destination. While traditional planning methods work "offline" (i.e., they take decisions for a batch of containers before the transportation starts), the proposed approach is "online", in that it can take decisions for individual containers, while transportation is being executed. Planning transportation online helps to effectively respond to unforeseen events that may affect the or…
