Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned on task completion. These task-conditioned models adaptively focus modeling capacity on task-relevant dynamics, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches.
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University Innsbruck（因斯布鲁克大学）
The ability to form complex plans based on raw visual input is a litmus test for current capabilities of artificial intelligence, as it requires a seamless combination of visual processing and abstract algorithmic execution, two traditionally separate areas of computer science. A recent surge of interest in this field brought advances that yield good performance in tasks ranging from arcade games to continuous control; these methods however do not come without significant issues, such as limited generalization capabilities and difficulties when dealing with combinatorially hard planning instan…
In searching for a generalizable representation of temporally extended tasks, we spot two necessary constituents: the utility needs to be non-Markovian to transfer temporal relations invariant to a probability shift, the utility also needs to be lifted to abstract out specific grounding objects. In this work, we study learning such utility from human demonstrations. While inverse reinforcement learning (IRL) has been accepted as a general framework of utility learning, its fundamental formulation is one concrete Markov Decision Process. Thus the learned reward function does not specify the tas…
UC Berkeley（加州大学伯克利分校）；Google Research（谷歌研究院）；University of Toronto（多伦多大学）；Covariant（协变机器人公司）
Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle commands, current artificial intelligence is limited to tasks with horizons of a few hundred decisions, despite large compute budgets. Research on hierarchical reinforcement learning aims to overcome this limitation but has proven to be challenging, current methods rely on manually specified goal spaces or subtasks, and no general solution exists. We introduce Director, a practical method for learning hierarchical behav…
Volkswagen AG（大众汽车公司）；Technische Universität Darmstadt（达姆施塔特工业大学）
Behavior and motion planning play an important role in automated driving. Traditionally, behavior planners instruct local motion planners with predefined behaviors. Due to the high scene complexity in urban environments, unpredictable situations may occur in which behavior planners fail to match predefined behavior templates. Recently, general-purpose planners have been introduced, combining behavior and local motion planning. These general-purpose planners allow behavior-aware motion planning given a single reward function. However, two challenges arise: First, this function has to map a comp…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Robert Bosch GmbH（罗伯特·博世有限公司）
Cooperative trajectory planning methods for automated vehicles can solve traffic scenarios that require a high degree of cooperation between traffic participants. However, for cooperative systems to integrate into human-centered traffic, the automated systems must behave human-like so that humans can anticipate the system's decisions. While Reinforcement Learning has made remarkable progress in solving the decision-making part, it is non-trivial to parameterize a reward model that yields predictable actions. This work employs feature-based Maximum Entropy Inverse Reinforcement Learning combine…
Key Lab of Machine Perception (MOE), Peking University（北京大学机器感知重点实验室（教育部））
Terrain traversability analysis is a fundamental issue to achieve the autonomy of a robot at off-road environments. Geometry-based and appearance-based methods have been studied in decades, while behavior-based methods exploiting learning from demonstration (LfD) are new trends. Behavior-based methods learn cost functions that guide trajectory planning in compliance with experts' demonstrations, which can be more scalable to various scenes and driving behaviors. This research proposes a method of off-road traversability analysis and trajectory planning using Deep Maximum Entropy Inverse Reinfo…
This paper focuses on inverse reinforcement learning for autonomous navigation using distance and semantic category observations. The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory. We develop a map encoder, that infers semantic category probabilities from the observation sequence, and a cost encoder, defined as a deep neural network over the semantic features. Since the expert cost is not directly observable, the model parameters can only be optimized by differentiating the error between de…
Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input. One successful approach, RolloutIW, represents states with the B-PROST boolean feature set. An augmented version of RolloutIW, $π$-IW, shows that learned features can be competitive with handcrafted ones for width-based search. In this paper, we leverage variational autoencoders (VAEs) to learn features directly from pixels in a principled manner, and without supervision. The inference model of the trained VAEs extracts boolean features from pixels, and RolloutIW plans…
Machine Learning (ML) has been embraced as a powerful tool by the financial industry, with notable applications spreading in various domains including investment management. In this work, we propose a full-cycle data-driven investment robo-advising framework, consisting of two ML agents. The first agent, an inverse portfolio optimization agent, infers an investor's risk preference and expected return directly from historical allocation data using online inverse optimization. The second agent, a deep reinforcement learning (RL) agent, aggregates the inferred sequence of expected returns to form…
Google Brain（谷歌大脑）；University of Toronto（多伦多大学）；DeepMind（深度思维）；Google Research（谷歌研究院）；University of Michigan（密歇根大学）
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately p…
Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning
Department of Psychology, University of Toronto（多伦多大学心理学系）；Vector Institute（向量研究所）；Schwartz Reisman Institute of Technology & Society, University of Toronto（多伦多大学科技与社会研究所）；Department of Computer Science, University of Toronto（多伦多大学计算机科学系）
While robots can learn models to solve many manipulation tasks from raw visual input, they cannot usually use these models to solve new problems. On the other hand, symbolic planning methods such as STRIPS have long been able to solve new problems given only a domain definition and a symbolic goal, but these approaches often struggle on the real world robotic tasks due to the challenges of grounding these symbols from sensor data in a partially-observable world. We propose Deep Planning Domain Learning (DPDL), an approach that combines the strengths of both methods to learn a hierarchical mode…
Planning is an important capability of artificial agents that perform long-horizon tasks in real-world environments. In this work, we explore the use of pre-trained language models (PLMs) to reason about plan sequences from text instructions in embodied visual environments. Prior PLM based approaches for planning either assume observations are available in the form of text (e.g., provided by a captioning model), reason about plans from the instruction alone, or incorporate information about the visual environment in limited ways (such as a pre-trained affordance function). In contrast, we show…
Rice University（莱斯大学）；Indian Institute of Technology (IIT) Madras（印度理工学院马德拉斯分校）；Insight Centre for Data Analytics（数据 analytics 洞察中心）
Signal reconstruction is a challenging aspect of computational imaging as it often involves solving ill-posed inverse problems. Recently, deep feed-forward neural networks have led to state-of-the-art results in solving various inverse imaging problems. However, being task specific, these networks have to be learned for each inverse problem. On the other hand, a more flexible approach would be to learn a deep generative model once and then use it as a signal prior for solving various inverse problems. We show that among the various state of the art deep generative models, autoregressive models…
Radiotherapy inverse planning often requires planners to modify parameters in the treatment planning system's objective function to produce clinically acceptable plans. Due to the manual steps in this process, plan quality can vary depending on the planning time available and the planner's skills. This study investigates two hyperparameter-tuning methods for automated inverse planning. Because this framework does not train a model on previously-optimized plans, it can be readily adapted to practice pattern changes, and plan quality is not limited by that of a training cohort. We selected 10 pa…
Volkswagen AG（大众汽车公司）；Technische Universität Darmstadt（达姆施塔特工业大学）
General-purpose trajectory planning algorithms for automated driving utilize complex reward functions to perform a combined optimization of strategic, behavioral, and kinematic features. The specification and tuning of a single reward function is a tedious task and does not generalize over a large set of traffic situations. Deep learning approaches based on path integral inverse reinforcement learning have been successfully applied to predict local situation-dependent reward functions using features of a set of sampled driving policies. Sample-based trajectory planning algorithms are able to a…
A learning-driven automatic planning framework for proton PBS treatments of H&N cancers
Department of Radiation Medicine and Applied Sciences, University of California at San Diego（放射医学与应用科学系，加州大学圣地亚哥分校）；Amazon Inc.（亚马逊公司）；California Protons Cancer Therapy Center（加利福尼亚质子癌症治疗中心）
Many algorithms and methods have been proposed for inverse problems particularly with the recent surge of interest in machine learning and deep learning methods. Among all proposed methods, the most popular and effective method is the convolutional neural network (CNN) with mean square error (MSE). This method has been proven effective in super-resolution, image de-noising, and image reconstruction. However, this method is known to over-smooth images due to the nature of MSE. MSE based methods minimize Euclidean distance for all pixels between a baseline image and a generated image by CNN and …
University of Edinburgh（爱丁堡大学）；Monash University（莫纳什大学）
Learning low-dimensional latent state space dynamics models has been a powerful paradigm for enabling vision-based planning and learning for control. We introduce a latent dynamics learning framework that is uniquely designed to induce proportional controlability in the latent space, thus enabling the use of much simpler controllers than prior work. We show that our learned dynamics model enables proportional control from pixels, dramatically simplifies and accelerates behavioural cloning of vision-based controllers, and provides interpretable goal discovery when applied to imitation learning …
Image segmentation is a very popular and important task in computer vision. In this paper, inverse quantum Fourier transform (IQFT) for image segmentation has been explored and a novel IQFT-inspired algorithm is proposed and implemented by leveraging the underlying mathematical structure of the IQFT. Specifically, the proposed method takes advantage of the phase information of the pixels in the image by encoding the pixels' intensity into qubit relative phases and applying IQFT to classify the pixels into different segments automatically and efficiently. To the best of our knowledge, this is t…
