Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the problem of automated data selection, or "intrinsic curiosity", remains a significant challenge. Classic approaches incentivize exploration by rewarding an agent based on its "learning progress", which measures how much a newly acquired observation improves a world model's predictive ability. However, evaluating these rewards traditionally requires expensive inner loops of gradient descent updates within each trajectory, rendering them computationally impractical at scale. In this work, we investigate whether the emergent in-context learning (ICL) capabilities of sequence models can eliminate this bottleneck by serving as immediate, update-free world models. Specifically, we evaluate whether an exploration policy can be trained to maximize learning progress, using solely the prediction errors and counterfactual context manipulations of an in-context learner. We first prove that in general Markov decision processes, this is in fact impossible in an unbiased way: the resulting intrinsic rewards either suffer from nuisance terms that bias their estimation of true learning progress, or they cannot be implemented using an in-context learner's prediction errors. Conversely, we prove a positive result for a broad subclass of non-temporal settings, encompassing active learning and Bayesian Experimental Design: here, ICL-derived rewards successfully bound and asymptotically converge to the true learning progress. We corroborate our theory with controlled experiments across continuous and symbolic environments, demonstrating that our ICL-driven framework successfully trains curious data-collection policies that explore optimally.
Korea Advanced Institute of Science and Technology（韩国科学技术院）
Intrinsic rewards have been increasingly used to mitigate the sparse reward problem in single-agent reinforcement learning. These intrinsic rewards encourage the agent to look for novel experiences, guiding the agent to explore the environment sufficiently despite the lack of extrinsic rewards. Curiosity-driven exploration is a simple yet efficient approach that quantifies this novelty as the prediction error of the agent's curiosity module, an internal neural network that is trained to predict the agent's next state given its current state and action. We show here, however, that naively using…
National University of Defense Technology（国防科技大学）；Artificial Intelligence Research Center, DII（国防创新研究院人工智能研究中心）
To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states. However, the intrinsic reward can be noisy due to the undesirable environment's stochasticity and directly applying the noisy value predictions to supervise the policy is detrimental to improve the learning performance and efficiency. Moreover, many previous studies employ $\ell^2$ norm or variance to measure the explo…
Psychological curiosity plays a significant role in human intelligence to enhance learning through exploration and information acquisition. In the Artificial Intelligence (AI) community, artificial curiosity provides a natural intrinsic motivation for efficient learning as inspired by human cognitive development; meanwhile, it can bridge the existing gap between AI research and practical application scenarios, such as overfitting, poor generalization, limited training samples, high computational cost, etc. As a result, curiosity-driven learning (CDL) has become increasingly popular, where agen…
Although there are many approaches to implement intrinsically motivated artificial agents, the combined usage of multiple intrinsic drives remains still a relatively unexplored research area. Specifically, we hypothesize that a mechanism capable of quantifying and controlling the evolution of the information flow between the agent and the environment could be the fundamental component for implementing a higher degree of autonomy into artificial intelligent agents. This paper propose a unified strategy for implementing two semantically orthogonal intrinsic motivations: curiosity and empowerment…
The Swiss AI Lab (IDSIA)（瑞士人工智能实验室（IDSIA））；University of Lugano (USI)（卢加诺大学（USI））；SUPSI（瑞士南部应用科学与艺术大学）；Google Research（谷歌研究院）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））；NNAISENSE
Efficient exploration in reinforcement learning is a challenging problem commonly addressed through intrinsic rewards. Recent prominent approaches are based on state novelty or variants of artificial curiosity. However, directly applying them to partially observable environments can be ineffective and lead to premature dissipation of intrinsic rewards. Here we propose random curiosity with general value functions (RC-GVF), a novel intrinsic reward function that draws upon connections between these distinct approaches. Instead of using only the current observation's novelty or a curiosity bonus…
University of Göttingen（哥廷根大学）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research（加拿大高等研究院）
Computer-aided design of molecules has the potential to disrupt the field of drug and material discovery. Machine learning, and deep learning, in particular, have been topics where the field has been developing at a rapid pace. Reinforcement learning is a particularly promising approach since it allows for molecular design without prior knowledge. However, the search space is vast and efficient exploration is desirable when using reinforcement learning agents. In this study, we propose an algorithm to aid efficient exploration. The algorithm is inspired by a concept known in the literature as …
Tsinghua University（清华大学）；Nanjing University（南京大学）；University of Alberta（阿尔伯塔大学）；NetEase（网易）
Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the "induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training.…
Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured …
OpenAI；UC Berkeley（加州大学伯克利分校）；Univ. of Edinburgh（爱丁堡大学）
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite. Our resul…
Albert Ludwig University of Freiburg（阿尔伯特-路德维希-弗莱堡大学）；The Hong Kong University of Science and Technology（香港科技大学）
This paper investigates exploration strategies of Deep Reinforcement Learning (DRL) methods to learn navigation policies for mobile robots. In particular, we augment the normal external reward for training DRL algorithms with intrinsic reward signals measured by curiosity. We test our approach in a mapless navigation setting, where the autonomous agent is required to navigate without the occupancy map of the environment, to targets whose relative locations can be easily acquired through low-cost solutions (e.g., visible light localization, Wi-Fi signal localization). We validate that the intri…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）
Reinforcement Learning enables to train an agent via interaction with the environment. However, in the majority of real-world scenarios, the extrinsic feedback is sparse or not sufficient, thus intrinsic reward formulations are needed to successfully train the agent. This work investigates and extends the paradigm of curiosity-driven exploration. First, a probabilistic approach is taken to exploit the advantages of the attention mechanism, which is successfully applied in other domains of Deep Learning. Combining them, we propose new methods, such as AttA2C, an extension of the Actor-Critic fr…
In this paper, we focus on a prediction-based novelty estimation strategy upon the deep reinforcement learning (DRL) framework, and present a flow-based intrinsic curiosity module (FICM) to exploit the prediction errors from optical flow estimation as exploration bonuses. We propose the concept of leveraging motion features captured between consecutive observations to evaluate the novelty of observations in an environment. FICM encourages a DRL agent to explore observations with unfamiliar motion features, and requires only two consecutive frames to obtain sufficient information when estimatin…
Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the future. In this paper a curiosity-driven agent is extended to use these predictions directly for training. To achieve this, the agent predicts the value function of the next state at any point in time. Subsequently, the consistency of this prediction with the current value function is measured, which is then used as a regularization term in the loss function of th…
Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the prediction error of a learned dynamics model as an intrinsic reward has been shown to be effective for exploring a number of sparse-reward environments. We present a method that combines hindsight with curiosity-driven exploration and curriculum learning in order to solve the challengin…
Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
Shanghai Jiao Tong University（上海交通大学）；School of Automation and Intelligent Sensing（自动化与智能感知学院）；Key Laboratory of System Control and Information Processing（系统控制与信息处理重点实验室）；Ministry of Education of China（中华人民共和国教育部）；National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家级重点实验室）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（脸书人工智能研究院）
Exploration is one of the core challenges in reinforcement learning. A common formulation of curiosity-driven exploration uses the difference between the real future and the future predicted by a learned model. However, predicting the future is an inherently difficult task which can be ill-posed in the face of stochasticity. In this paper, we introduce an alternative form of curiosity that rewards novel associations between different senses. Our approach exploits multiple modalities to provide a stronger signal for more efficient exploration. Our method is inspired by the fact that, for humans…
The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip current techniques for control, such as Reinforcement Learning, with more natural exploration capabilities. A promising approach in this respect has consisted of using Bayesian surprise on model parameters, i.e. a metric for the difference between prior and posterior beliefs, to favour exploration. In this contribution, we propose to apply Bayesian surprise in a latent space representing the agent's current un…
With reinforcement learning, an agent could learn complex behaviors from high-level abstractions of the task. However, exploration and reward shaping remained challenging for existing methods, especially in scenarios where the extrinsic feedback was sparse. Expert demonstrations have been investigated to solve these difficulties, but a tremendous number of high-quality demonstrations were usually required. In this work, an integrated policy gradient algorithm was proposed to boost exploration and facilitate intrinsic reward learning from only limited number of demonstrations. We achieved this …
Hong Kong University of Science and Technology（香港科技大学）
The design of recommendations strategies in the adaptive learning system focuses on utilizing currently available information to provide individual-specific learning instructions for learners. As a critical motivate for human behaviors, curiosity is essentially the drive to explore knowledge and seek information. In a psychologically inspired view, we aim to incorporate the element of curiosity for guiding learners to study spontaneously. In this paper, a curiosity-driven recommendation policy is proposed under the reinforcement learning framework, allowing for a both efficient and enjoyable p…
Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory. Children, however, benefit from exposure to language, helping to organize and mediate their thought. We propose LE2 (Language Enhanced Exploration), a learning algorithm leveraging intrinsic motivations and natural language (NL) interactions with a descriptive social partner (SP). Using NL descriptions from the SP, it can learn an NL-conditioned reward function to f…
South Westphalia University of Applied Sciences（西南法伦应用科学大学）
This paper introduces a novel combination of scheduling control on a flexible robot manufacturing cell with curiosity based reinforcement learning. Reinforcement learning has proved to be highly successful in solving tasks like robotics and scheduling. But this requires hand tuning of rewards in problem domains like robotics and scheduling even where the solution is not obvious. To this end, we apply a curiosity based reinforcement learning, using intrinsic motivation as a form of reward, on a flexible robot manufacturing cell to alleviate this problem. Further, the learning agents are embedde…
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and, c…
CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
Tencent AI Lab（腾讯AI实验室）；Tencent Multimodal Department（腾讯多模态部门）；University of North Carolina at Chapel Hill（北卡罗来纳大学夏洛特分校）；University of Virginia（弗吉尼亚大学）；University of Maryland, College Park（马里兰大学学院公园分校）
Capsule Networks (CapsNets) have been proposed as an alternative to Convolutional Neural Networks (CNNs). This paper showcases how CapsNets are more capable than CNNs for autonomous agent exploration of realistic scenarios. In real world navigation, rewards external to agents may be rare. In turn, reinforcement learning algorithms can struggle to form meaningful policy functions. This paper's approach Capsules Exploration Module (Caps-EM) pairs a CapsNets architecture with an Advantage Actor Critic algorithm. Other approaches for navigating sparse environments require intrinsic reward generato…
Indian Institute of Technology Jodhpur（焦特布尔印度理工学院）
Biological infants are naturally curious and try to comprehend their physical surroundings by interacting, in myriad multisensory ways, with different objects - primarily macroscopic solid objects - around them. Through their various interactions, they build hypotheses and predictions, and eventually learn, infer and understand the nature of the physical characteristics and behavior of these objects. Inspired thus, we propose a model for curiosity-driven learning and inference for real-world AI agents. This model is based on the arousal of curiosity, deriving from observations along discontinu…
Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $ε$-greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that have already been explored. We introduce a novel method based on Bayesian linear regression and latent space embedding to generate an intrinsic reward signal that encourages the learning agent to seek out unexplored parts of the state space. This method is computationally efficient…
Stanford University（斯坦福大学）；University of Washington（华盛顿大学）
Modern multi-agent reinforcement learning frameworks rely on centralized training and reward shaping to perform well. However, centralized training and dense rewards are not readily available in the real world. Current multi-agent algorithms struggle to learn in the alternative setup of decentralized training or sparse rewards. To address these issues, we propose a self-supervised intrinsic reward ELIGN - expectation alignment - inspired by the self-organization principle in Zoology. Similar to how animals collaborate in a decentralized manner with those in their vicinity, agents trained with …
VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness
State Key Laboratory of Intelligent Transportation Systems（智能交通系统国家重点实验室）；School of Transportation Science and Technology, Beihang University（北京航空航天大学交通科学与工程学院）；Department of Civil and Environmental Engineering, Rensselaer Polytechnic Institute（伦斯勒理工学院土木与环境工程系）
Massachusetts Institute of Technology（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Aalto University（阿尔托大学）
State-of-the-art reinforcement learning (RL) algorithms typically use random sampling (e.g., $ε$-greedy) for exploration, but this method fails on hard exploration tasks like Montezuma's Revenge. To address the challenge of exploration, prior works incentivize exploration by rewarding the agent when it visits novel states. Such intrinsic rewards (also called exploration bonus or curiosity) often lead to excellent performance on hard exploration tasks. However, on easy exploration tasks, the agent gets distracted by intrinsic rewards and performs unnecessary exploration even when sufficient tas…
Collective behavior is widespread across the animal kingdom. To date, however, the developmental and mechanistic foundations of collective behavior have not been formally established. What learning mechanisms drive the development of collective behavior in newborn animals? Here, we used deep reinforcement learning and curiosity-driven learning -- two learning mechanisms deeply rooted in psychological and neuroscientific research -- to build newborn artificial agents that develop collective behavior. Like newborn animals, our agents learn collective behavior from raw sensory inputs in naturalis…
Technische Universität Darmstadt（达姆施塔特工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion. A principled treatment of the problem of optimal input synthesis for system identification is provided within the framework of sequential Bayesian experimental design. In this paper, we present an effective trajectory-optimization-based approximate solution of this otherwise intractable problem that models optimal exploration in an unknown Markov decision process (MDP). By interleaving episodic exploration with Bayesian nonlinear system…
Inria - Flowers team（法国国家信息与自动化研究所花朵团队）；Université de Bordeaux（波尔多大学）；Inserm U1093（法国国家健康与医学研究院U1093）；Cloud Temple（云庙）；Paris（巴黎）；ENSTA ParisTech（巴黎高等科技学院）；Université de Dijon（第戎大学）
Developmental machine learning studies how artificial agents can model the way children learn open-ended repertoires of skills. Such agents need to create and represent goals, select which ones to pursue and learn to achieve them. Recent approaches have considered goal spaces that were either fixed and hand-defined or learned using generative models of states. This limited agents to sample goals within the distribution of known effects. We argue that the ability to imagine out-of-distribution goals is key to enable creative discoveries and open-ended learning. Children do so by leveraging the …
Baby Sophia: A Developmental Approach to Self-Exploration through Self-Touch and Hand Regard
Robotics Institute, Athena Research Center（机器人研究所，阿提卡研究中心）；HERON – Hellenic Robotics Center of Excellence（HERON – 希腊机器人 excellence 中心）；Institute for Language and Speech Processing, Athena Research Center（语言和语音处理研究所，阿提卡研究中心）
TECNALIA, Basque Research and Technology Alliance (BRTA)（TECNALIA，巴斯克研究与技术联盟（BRTA））；University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））
Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or bad) the decisions made by the learned agent are. Unfortunately, in a broad range of problems the design of a good reward function is not trivial, so in such cases sparse reward signals are instead adopted. The lack of a dense reward function poses new challenges, mostly related to exploration. Imitation Learning has addressed those problems by leveraging demon…
I postulate that human or other intelligent agents function or should function as follows. They store all sensory observations as they come - the data is holy. At any time, given some agent's current coding capabilities, part of the data is compressible by a short and hopefully fast program / description / explanation / world model. In the agent's subjective eyes, such data is more regular and more "beautiful" than other data. It is well-known that knowledge of regularity and repeatability may improve the agent's ability to plan actions leading to external rewards. In absence of such rewards, …
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which the agent can move and interact with objects it sees, the agent learns a world model predicting the dynamic consequences of its actions. Simultaneously, the agent learns to take actions that adversarially challenge the developing world …
What are the functions of curiosity? What are the mechanisms of curiosity-driven learning? We approach these questions about the living using concepts and tools from machine learning and developmental robotics. We argue that curiosity-driven learning enables organisms to make discoveries to solve complex problems with rare or deceptive rewards. By fostering exploration and discovery of a diversity of behavioural skills, and ignoring these rewards, curiosity can be efficient to bootstrap learning when there is no information, or deceptive information, about local improvement towards these probl…
