In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in visual grasping and manipulation. Leveraging action-conditioned video prediction, we propose an end-to-end learning framework to disentangle the controllable object from the observation signal. The disentangled representation is shown to be useful for RL as additional observation channels to the agent. Experiments on a set of Atari games with the popular Double DQN algorithm demonstrate improved sample efficiency and game performance (from 222.8% to 261.4% measured in normalized game scores, with prediction bonus reward).
Two hitherto disconnected threads of research, diverse exploration (DE) and maximum entropy RL have addressed a wide range of problems facing reinforcement learning algorithms via ostensibly distinct mechanisms. In this work, we identify a connection between these two approaches. First, a discriminator-based diversity objective is put forward and connected to commonly used divergence measures. We then extend this objective to the maximum entropy framework and propose an algorithm Maximum Entropy Diverse Exploration (MEDE) which provides a principled method to learn diverse behaviors. A theoret…
TU Darmstadt（达姆施塔特工业大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tampere University（坦佩雷大学）
Deep learning in combination with improved training techniques and high computational power has led to recent advances in the field of reinforcement learning (RL) and to successful robotic RL applications such as in-hand manipulation. However, most robotic RL relies on a well known initial state distribution. In real-world tasks, this information is however often not available. For example, when disentangling waste objects the actual position of the robot w.r.t.\ the objects may not match the positions the RL policy was trained for. To solve this problem, we present a novel adversarial reinfor…
Jagiellonian University（雅盖隆大学）；DeepMind（深度思维）；Polish Academy of Sciences（波兰科学院）；Ideas NCBR（Ideas国家研究与发展中心）
The ability of continual learning systems to transfer knowledge from previously seen tasks in order to maximize performance on new tasks is a significant challenge for the field, limiting the applicability of continual learning solutions to realistic scenarios. Consequently, this study aims to broaden our understanding of transfer and its driving forces in the specific case of continual reinforcement learning. We adopt SAC as the underlying RL algorithm and Continual World as a suite of continuous control tasks. We systematically study how different components of SAC (the actor and the critic,…
Technical University of Munich（慕尼黑工业大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Stanford University（斯坦福大学）；Stanford Intelligent Systems Laboratory（斯坦福智能系统实验室）
Characterizing aleatoric and epistemic uncertainty on the predicted rewards can help in building reliable reinforcement learning (RL) systems. Aleatoric uncertainty results from the irreducible environment stochasticity leading to inherently risky states and actions. Epistemic uncertainty results from the limited information accumulated during learning to make informed decisions. Characterizing aleatoric and epistemic uncertainty can be used to speed up learning in a training environment, improve generalization to similar testing environments, and flag unfamiliar behavior in anomalous testing …
In reinforcement learning (RL), temporal abstraction still remains as an important and unsolved problem. The options framework provided clues to temporal abstraction in the RL, and the option-critic architecture elegantly solved the two problems of finding options and learning RL agents in an end-to-end manner. However, it is necessary to examine whether the options learned through this method play a mutually exclusive role. In this paper, we propose a Hellinger distance regularizer, a method for disentangling options. In addition, we will shed light on various indicators from the statistical …
University of Tartu（塔尔图大学）；Institute of Computer Science（计算机科学研究所）
Exploration and credit assignment under sparse rewards are still challenging problems. We argue that these challenges arise in part due to the intrinsic rigidity of operating at the level of actions. Actions can precisely define how to perform an activity but are ill-suited to describe what activity to perform. Instead, causal effects are inherently composable and temporally abstract, making them ideal for descriptive tasks. By leveraging a hierarchy of causal effects, this study aims to expedite the learning of task-specific behavior and aid exploration. Borrowing counterfactual and normality…
Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning
Zhejiang University（浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；School of Software Technology, Zhejiang University（浙江大学软件学院）
Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks. We show that this learned subspace enables efficient …
Motion synthesis in a dynamic environment has been a long-standing problem for character animation. Methods using motion capture data tend to scale poorly in complex environments because of their larger capturing and labeling requirement. Physics-based controllers are effective in this regard, albeit less controllable. In this paper, we present CARL, a quadruped agent that can be controlled with high-level directives and react naturally to dynamic environments. Starting with an agent that can imitate individual animation clips, we use Generative Adversarial Networks to adapt high-level control…
Tianjin University（天津大学）；Tencent（腾讯）；The Chinese University of Hong Kong（香港中文大学）
Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward signals. In this paper, we propose a two-step understanding of value estimation from the perspective of future prediction, through decomposing the value function into a reward-independent future dynamics part and a policy-independent trajectory return part. We then derive a practical deep RL algorithm from the above decomposition, consisting of a convolutional t…
Reinforcement Learning to Disentangle Multiqubit Quantum States from Partial Observations
Department of Mathematics and Informatics（数学与信息学系）；St. Kliment Ohridski University of Sofia（索菲亚圣克莱门特·欧赫里迪斯大学）；Joint Quantum Institute（联合量子研究所）；Department of Physics（物理系）；University of Maryland（马里兰大学）；National Quantum Laboratory (QLab)（国家量子实验室（QLab））；Institute of Physics（物理研究所）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院（EPFL））；Center for Quantum Science and Engineering（量子科学与工程中心）；Quantum Systems Unit（量子系统单元）；OIST Graduate University（OIST研究生大学）；Duke Quantum Center（杜克量子中心）；Max Planck Institute for the Physics of Complex Systems（复杂系统物理研究所）
Rutgers University, The State University of New Jersey（罗格斯大学（新泽西州立大学））
The aim of path planning is to reach the goal from starting point by searching for the route of an agent. In the path planning, the routes may vary depending on the number of variables such that it is important for the agent to reach various goals. Numerous studies, however, have dealt with a single goal that is predefined by the user. In the present study, I propose a novel reinforcement learning framework for a fully controllable agent in the path planning. To do this, I propose a bi-directional memory editing to obtain various bi-directional trajectories of the agent, in which the behavior …
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zurich（苏黎世联邦理工学院）
To successfully tackle challenging manipulation tasks, autonomous agents must learn a diverse set of skills and how to combine them. Recently, self-supervised agents that set their own abstract goals by exploiting the discovered structure in the environment were shown to perform well on many different tasks. In particular, some of them were applied to learn basic manipulation skills in compositional multi-object environments. However, these methods learn skills without taking the dependencies between objects into account. Thus, the learned skills are difficult to combine in realistic environme…
Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty arises from stochastic environments and must be accounted for in risk-sensitive applications. We highlight the challenges involved in simultaneously estimating both of them, and propose a framework for disentangling and estimating these uncertainties on learned Q-values. We derive unbiased estimators of these uncertainties and introduce an uncertainty-aware DQN algorithm, which we show exhibits safe learning behavior a…
MILA（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）；Element AI（元素人工智能公司）；McGill University（麦吉尔大学）；ENS Paris（巴黎高等师范学院）；Google Brain（谷歌大脑）；Facebook AI Research（脸书人工智能研究院）；Google Deepmind（谷歌DeepMind）
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environ…
LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric Translation
School of Informatics, Xiamen University（厦门大学信息学院）；School of Journalism and Communication, Xiamen University（厦门大学新闻传播学院）；School of Film, Xiamen University（厦门大学电影学院）；Xiamen Key Laboratory of Intelligent Storage and Computing, Xiamen University（厦门大学智能存储与计算重点实验室）；Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院）
This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning. To investigate this question, we consider an instantiation of this hypothesis evaluated on the Arcade Learning Element (ALE). In this study, we develop an attentive dynamics model (ADM) that discovers controllable elements of the observations, which are often associated with the location of the character in Atari games. The ADM is trained in a self-supervised fashion to predict the actions taken by the agent. The learned contingency…
Learning controllable dynamics through informative exploration
School of Science（科学与技术学院）；University of New England Australia（新英格兰大学澳大利亚分校）；Redwood Center for Theoretical Neuroscience（红木理论神经科学中心）；University of California at Berkeley USA（加州大学伯克利分校美国分校）
KAIST（韩国科学技术院）；Klleon AI Research（Klleon人工智能研究院）；UNIST（蔚山国立科学技术院）
Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still challenging. Existing methods often require additional models, which is computationally demanding and leads to unsatisfactory visual quality. In addition, they have restricted control steps, which prevents a smooth transition. In this paper, we propose a new approach for high-quality domain translation with better controllability. The key idea is to preserve s…
Fraunhofer Institute für Produktionsanlagen und Konstruktionstechnik (IPK)（弗劳恩霍夫生产设备与结构技术研究所（IPK））
Learned representations of dynamical systems reduce dimensionality, potentially supporting downstream reinforcement learning (RL). However, no established methods predict a representation's suitability for control and evaluation is largely done via downstream RL performance, slowing representation design. Towards a principled evaluation of representations for control, we consider the relationship between the true state and the corresponding representations, proposing that ideally each representation corresponds to a unique true state. This motivates two metrics: temporal smoothness and high mu…
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology（哈尔滨工业大学社会计算与交互机器人研究中心）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
Siemens AG（西门子公司）；Ludwig Maximilian University of Munich（慕尼黑大学）；University of California, Berkeley（加州大学伯克利分校）；Horizon Robotics（地平线机器人技术公司）
In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states. This objective encourages the agent to take control of its environment. Subsequently, we derive a surrogate objective of the proposed reward function, which can be optimized eff…
Imperial College London（帝国理工学院）；University of Bath（巴斯大学）；Shanghaitech University（上海科技大学）
This paper presents a problem in power networks that creates an exciting and yet challenging real-world scenario for application of multi-agent reinforcement learning (MARL). The emerging trend of decarbonisation is placing excessive stress on power distribution networks. Active voltage control is seen as a promising solution to relieve power congestion and improve voltage quality without extra hardware investment, taking advantage of the controllable apparatuses in the network, such as roof-top photovoltaics (PVs) and static var compensators (SVCs). These controllable apparatuses appear in a …
Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable objects and universal value function approximator learning for controllable objects. Such decomposition should lead to a shorter learning time and better generalisation capability. Here, we consider arcade-game environments as sets of interacting objects (controllable, non-controllable) and propose a set of functional modules that are specialized on masterin…
Credit assignment in reinforcement learning is the problem of measuring an action's influence on future rewards. In particular, this requires separating skill from luck, i.e. disentangling the effect of an action on rewards from that of external factors and subsequent actions. To achieve this, we adapt the notion of counterfactuals from causality theory to a model-free RL setup. The key idea is to condition value functions on future events, by learning to extract relevant information from a trajectory. We formulate a family of policy gradient algorithms that use these future-conditional value …
This paper introduces a set of formally defined and transparent problems for reinforcement learning algorithms with the following characteristics: (1) variable degrees of observability (non-Markov observations), (2) distal and sparse rewards, (3) variable and hierarchical reward structure, (4) multiple-task generation, (5) variable problem complexity. The environment provides 1D or 2D categorical observations, and takes actions as input. The core structure of the CT-graph is a multi-branch tree graph with arbitrary branching factor, depth, and observation sets that can be varied to increase th…
Impressive results in natural language processing (NLP) based on the Transformer neural network architecture have inspired researchers to explore viewing offline reinforcement learning (RL) as a generic sequence modeling problem. Recent works based on this paradigm have achieved state-of-the-art results in several of the mostly deterministic offline Atari and D4RL benchmarks. However, because these methods jointly model the states and actions as a single sequencing problem, they struggle to disentangle the effects of the policy and world dynamics on the return. Thus, in adversarial or stochast…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Off-policy reinforcement learning (RL) is concerned with learning a rewarding policy by executing another policy that gathers samples of experience. While the former policy (i.e. target policy) is rewarding but in-expressive (in most cases, deterministic), doing well in the latter task, in contrast, requires an expressive policy (i.e. behavior policy) that offers guided and effective exploration. Contrary to most methods that make a trade-off between optimality and expressiveness, disentangled frameworks explicitly decouple the two objectives, which each is dealt with by a distinct separate po…
We present Mask Atari, a new benchmark to help solve partially observable Markov decision process (POMDP) problems with Deep Reinforcement Learning (DRL)-based approaches. To achieve a simulation environment for the POMDP problems, Mask Atari is constructed based on Atari 2600 games with controllable, moveable, and learnable masks as the observation area for the target agent, especially with the active information gathering (AIG) setting in POMDPs. Given that one does not yet exist, Mask Atari provides a challenging, efficient benchmark for evaluating the methods that focus on the above proble…
McGill University（麦吉尔大学）；Valence Labs（Valence实验室）；Mila - Québec AI Institute（米拉-魁北克人工智能研究所）；Google Deepmind（谷歌DeepMind）；Hong Kong University of Science and Technology（香港科技大学）
It has recently been shown that reinforcement learning can be used to train generators capable of producing high-quality game levels, with quality defined in terms of some user-specified heuristic. To ensure that these generators' output is sufficiently diverse (that is, not amounting to the reproduction of a single optimal level configuration), the generation process is constrained such that the initial seed results in some variance in the generator's output. However, this results in a loss of control over the generated content for the human user. We propose to train generators capable of pro…
Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraints, using computable, user-defined measures of quality instead of target output. We explore the application of PCGRL to 3D domains, in which content-generation tasks naturally have greater complexity and potential pertinence to real-world applications. Here, we introduce several PCGRL tasks for the 3D domain, Minecraft (Mojang Studios, 2009). These tasks will challenge RL-based generators using affordances often found…
Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator. This can lead to slow learning, or convergence to suboptimal policies, if the environment variable has a large impact on the transition dynamics. In this paper, we present fingerprint policy optimisation (FPO), which finds a policy that is optimal in expectation across the distribution of environment variables. The central idea is to use Bayesian optimisation (BO) to activel…
Leibniz University Hanover（莱布尼茨汉诺威大学）；University of Freiburg（弗赖堡大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
While Reinforcement Learning has made great strides towards solving ever more complicated tasks, many algorithms are still brittle to even slight changes in their environment. This is a limiting factor for real-world applications of RL. Although the research community continuously aims at improving both robustness and generalization of RL algorithms, unfortunately it still lacks an open-source set of well-defined benchmark problems based on a consistent theoretical framework, which allows comparing different approaches in a fair, reliable and reproducibleway. To fill this gap, we propose CARL,…
Shandong Provincial Key Laboratory of Network Based Intelligent Computing（山东省网络智能计算重点实验室）；University of Jinan（济南大学）；Jinan, 250022, China（济南市，250022，中国）
Disentanglement is a highly desirable property of representation due to its similarity with human's understanding and reasoning. This improves interpretability, enables the performance of down-stream tasks, and enables controllable generative models. However, this domain is challenged by the abstract notion and incomplete theories to support unsupervised disentanglement learning. We demonstrate the data itself, such as the orientation of images, plays a crucial role in disentanglement and instead of the factors, and the disentangled representations align the latent variables with the action se…
ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy
Zhejiang University（浙江大学）；Ningbo Global Innovation Center, Zhejiang University（浙江大学宁波全球创新中心）；Zhejiang Key Laboratory of Digital-Intelligence Service Technology（浙江省数字智能服务技术重点实验室）；Xidian University（西安电子科技大学）
