Reinforcement learning (RL) has drawn increasing interests in recent years due to its tremendous success in various applications. However, standard RL algorithms can only be applied for single reward function, and cannot adapt to an unseen reward function quickly. In this paper, we advocate a general operator view of reinforcement learning, which enables us to directly approximate the operator that maps from reward function to value function. The benefit of learning the operator is that we can incorporate any new reward function as input and attain its corresponding value function in a zero-shot manner. To approximate this special type of operator, we design a number of novel operator neural network architectures based on its theoretical properties. Our design of operator networks outperform the existing methods and the standard design of general purpose operator network, and we demonstrate the benefit of our operator deep Q-learning framework in several tasks including reward transferring for offline policy evaluation (OPE) and reward transferring for offline policy optimization in a range of tasks.
Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning. Knowledge acquired during an unsupervised pre-training phase is often transferred by fine-tuning neural network weights once rewards are exposed, as is common practice in supervised domains. Given the nature of the reinforcement learning problem, we argue that standard fine-tuning strategies alone are not enough for efficient transfer in challenging domains. We introduce Behavior Transfer (BT), a technique that leverages pre-trained policies for ex…
It is a long-standing challenge to enable an intelligent agent to learn in one environment and generalize to an unseen environment without further data collection and finetuning. In this paper, we consider a zero shot generalization problem setup that complies with biological intelligent agents' learning and generalization processes. The agent is first presented with previous experiences in the training environment, along with task description in the form of trajectory-level sparse rewards. Later when it is placed in the new testing environment, it is asked to perform the task without any inte…
GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO
College of Computing and Data Science,Nanyang Technological University (NTU), Singapore（南洋理工大学计算与数据科学学院）；Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly(LILY),NTU,Singapore（南洋理工大学与UBC联合卓越老年活跃生活研究中心（LILY））
PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；King’s College London（伦敦国王学院）；Beijing Institute for General AI（北京通用人工智能研究院）；Shanghai Jiao Tong University（上海交通大学）
University of Kentucky（肯塔基大学）；University of Central Florida（中佛罗里达大学）
Task-oriented dialog systems enable users to accomplish tasks using natural language. State-of-the-art systems respond to users in the same way regardless of their personalities, although personalizing dialogues can lead to higher levels of adoption and better user experiences. Building personalized dialog systems is an important, yet challenging endeavor and only a handful of works took on the challenge. Most existing works rely on supervised learning approaches and require laborious and expensive labeled training data for each user profile. Additionally, collecting and labeling data for each…
While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and policy exploitation. Preference based RL algorithms seek to overcome these challenges by directly learning reward functions from human feedback. Unfortunately, prior work either requires an unreasonable number of queries implausible for any human to answer or overly restricts the class of reward functions to guarantee the elicitation of the most informative qu…
We present O2A, a novel method for learning to perform robotic manipulation tasks from a single (one-shot) third-person demonstration video. To our knowledge, it is the first time this has been done for a single demonstration. The key novelty lies in pre-training a feature extractor for creating a perceptual representation for actions that we call 'action vectors'. The action vectors are extracted using a 3D-CNN model pre-trained as an action classifier on a generic action dataset. The distance between the action vectors from the observed third-person demonstration and trial robot executions i…
Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；TikTok Pte. Ltd., Singapore（新加坡TikTok公司）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）；Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电气与计算机工程系）
We consider the task of Inverse Reinforcement Learning in Contextual Markov Decision Processes (MDPs). In this setting, contexts, which define the reward and transition kernel, are sampled from a distribution. In addition, although the reward is a function of the context, it is not provided to the agent. Instead, the agent observes demonstrations from an optimal policy. The goal is to learn the reward mapping, such that the agent will act optimally even when encountering previously unseen contexts, also known as zero-shot transfer. We formulate this problem as a non-differential convex optimiz…
Reward design in reinforcement learning (RL) is challenging since specifying human notions of desired behavior may be difficult via reward functions or require many expert demonstrations. Can we instead cheaply design rewards using a natural language interface? This paper explores how to simplify reward design by prompting a large language model (LLM) such as GPT-3 as a proxy reward function, where the user provides a textual prompt containing a few examples (few-shot) or a description (zero-shot) of the desired behavior. Our approach leverages this proxy reward function in an RL framework. Sp…
Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a fixed goal and in a known environment, on a mobile robot. The robot leverages an interactive world model built from a single traversal of the environment, a pre-trained visual feature encoder, and stoch…
Zhejiang University（浙江大学）；Westlake University（西湖大学）；UC Berkeley（加州大学伯克利分校）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院前沿技术研究所）
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure is often time-consuming, limiting the rollout in some potentially expensive target environments. The intuitive approach of training in another interaction-rich environment disrupts the reproducibility of trained skills in the target environment due to the dynamics shifts and thus inhibits direct transferring. Assuming free access to a source environment, we…
University of Kansas（堪萨斯大学）；University of New Mexico（新墨西哥大学）；Iran University of Science and Technology（伊朗科技大学）
Potential-based reward shaping (PBRS) is a particular category of machine learning methods which aims to improve the learning speed of a reinforcement learning agent by extracting and utilizing extra knowledge while performing a task. There are two steps in the process of transfer learning: extracting knowledge from previously learned tasks and transferring that knowledge to use it in a target task. The latter step is well discussed in the literature with various methods being proposed for it, while the former has been explored less. With this in mind, the type of knowledge that is transmitted…
We are motivated by the goal of generalist robots that can complete a wide range of tasks across many environments. Critical to this is the robot's ability to acquire some metric of task success or reward, which is necessary for reinforcement learning, planning, or knowing when to ask for help. For a general-purpose robot operating in the real world, this reward function must also be able to generalize broadly across environments, tasks, and objects, while depending only on on-board sensor observations (e.g. RGB images). While deep learning on large and diverse datasets has shown promise as a …
A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase. This marks a shift from the reward-centric RL paradigm towards "controllable" agents that can follow arbitrary instructions in an environment. Current RL agents can solve families of related tasks at best, or require planning anew for each task. Strategies for approximate zero-shot RL ave been suggested using successor features (SFs) [BBQ+ 18] or forward-backward (FB) representations [TO21], but testing has been limi…
Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models. We perform in-context learning distillation under two different few-shot learning paradigms: Meta In-context Tuning (Meta-ICT) and Multitask In-context Tuning (Multitask-ICT). Multitask-ICT performs bet…
University of Science and Technology Beijing（北京科技大学）；Tsinghua University（清华大学）
Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems. Supervised knowledge can significantly improve the performance. However, faced with the rapid growth of newly emerging concepts, existing supervised methods might easily suffer from the scarcity and validity of labeled data for training. In this paper, the authors study the problem of zero-shot feature selection (i.e., building a feature selection model that generalizes well to "unseen" concepts with limited training data of "seen" concepts). Specifically, they adop…
The ALTA Institute（ALTA研究所）；Computer Laboratory（计算机实验室）；University of Cambridge（剑桥大学）；United Kingdom（英国）；CoAStaL DIKU（CoAStaL DIKU（此处“DIKU”为丹麦哥本哈根大学计算机科学系缩写，按原文保留））；Department of Computer Science（计算机科学系）；University of Copenhagen（哥本哈根大学）；Denmark（丹麦）
Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on soft attention, train it as a binary sentence classifier and evaluate against token-level annotation on four different datasets. Inferring token labels from a network provides a method for quantitatively evaluating what the model is learning, along with generating useful feedback in assistance systems. Our results indicate that attention-based methods are able…
Anomaly Multi-classification in Industrial Scenarios: Transferring Few-shot Learning to a New Task
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能全国重点实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究所）；Xi’an Jiaotong University（西安交通大学）；School of Informatics（信息学院）；Xiamen University（厦门大学）；College of Mechatronics and Control Engineering（机电与控制工程学院）；Shenzhen University（深圳大学）
本文提出工业异常多分类新任务，通过结合 RelationNet 与 PatchCore、伪类数据生成及对比学习，在 MvTec AD 和 MvTec3D AD 上取得优于直接微调 ResNet 的性能。
A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances. We introduce a general mechanism for automatically specifying meaningful behaviors from raw pixels. In particular, we train a generative adversarial network to produce short sub-goals represented through motion templates. We demonstrate that this approach generates visually meaningful behaviors in unknown environments with novel agents and describe how these motions can be used to train reinforcement learning agents.
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization (muP), many optimal HPs remain stable even as model size changes. This leads to a new HP tuning paradigm we call muTransfer: parametrize the target model in muP, tune the HP indirectly on a smaller model, and zero-shot transfer them to the full-sized model, i.e., without directly tuning the latter at all. We verify muTransfer on Transformer and ResNet. For example, 1) by transferring …
Making changes to a program to optimize its performance is an unscalable task that relies entirely upon human intuition and experience. In addition, companies operating at large scale are at a stage where no single individual understands the code controlling its systems, and for this reason, making changes to improve performance can become intractably difficult. In this paper, a learning system is introduced that provides AI assistance for finding recommended changes to a program. Specifically, it is shown how the evaluative feedback, delayed-reward performance programming domain can be effect…
