Imitation learning has been widely applied to various autonomous systems thanks to recent development in interactive algorithms that address covariate shift and compounding errors induced by traditional approaches like behavior cloning. However, existing interactive imitation learning methods assume access to one perfect expert. Whereas in reality, it is more likely to have multiple imperfect experts instead. In this paper, we propose MEGA-DAgger, a new DAgger variant that is suitable for interactive learning with multiple imperfect experts. First, unsafe demonstrations are filtered while aggregating the training data, so the imperfect demonstrations have little influence when training the novice policy. Next, experts are evaluated and compared on scenarios-specific metrics to resolve the conflicted labels among experts. Through experiments in autonomous racing scenarios, we demonstrate that policy learned using MEGA-DAgger can outperform both experts and policies learned using the state-of-the-art interactive imitation learning algorithm. The supplementary video can be found at //youtu.be/pYQiPSHk6dU.
相關內容
We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments. We used Deep RL to train a humanoid robot with 20 actuated joints to play a simplified one-versus-one (1v1) soccer game. We first trained individual skills in isolation and then composed those skills end-to-end in a self-play setting. The resulting policy exhibits robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more; and transitions between them in a smooth, stable, and efficient manner - well beyond what is intuitively expected from the robot. The agents also developed a basic strategic understanding of the game, and learned, for instance, to anticipate ball movements and to block opponent shots. The full range of behaviors emerged from a small set of simple rewards. Our agents were trained in simulation and transferred to real robots zero-shot. We found that a combination of sufficiently high-frequency control, targeted dynamics randomization, and perturbations during training in simulation enabled good-quality transfer, despite significant unmodeled effects and variations across robot instances. Although the robots are inherently fragile, minor hardware modifications together with basic regularization of the behavior during training led the robots to learn safe and effective movements while still performing in a dynamic and agile way. Indeed, even though the agents were optimized for scoring, in experiments they walked 156% faster, took 63% less time to get up, and kicked 24% faster than a scripted baseline, while efficiently combining the skills to achieve the longer term objectives. Examples of the emergent behaviors and full 1v1 matches are available on the supplementary website.
Compressed sensing magnetic resonance imaging (CS-MRI) seeks to recover visual information from subsampled measurements for diagnostic tasks. Traditional CS-MRI methods often separately address measurement subsampling, image reconstruction, and task prediction, resulting in suboptimal end-to-end performance. In this work, we propose TACKLE as a unified framework for designing CS-MRI systems tailored to specific tasks. Leveraging recent co-design techniques, TACKLE jointly optimizes subsampling, reconstruction, and prediction strategies to enhance the performance on the downstream task. Our results on multiple public MRI datasets show that the proposed framework achieves improved performance on various tasks over traditional CS-MRI methods. We also evaluate the generalization ability of TACKLE by experimentally collecting a new dataset using different acquisition setups from the training data. Without additional fine-tuning, TACKLE functions robustly and leads to both numerical and visual improvements.
The hierarchy of global and local planners is one of the most commonly utilized system designs in robot autonomous navigation. While the global planner generates a reference path from the current to goal locations based on the pre-built static map, the local planner produces a collision-free, kinodynamic trajectory to follow the reference path while avoiding perceived obstacles. The reference path should be replanned regularly to accommodate new obstacles that were absent in the pre-built map, but when to execute replanning remains an open question. In this work, we conduct an extensive simulation experiment to compare various replanning strategies and confirm that effective strategies highly depend on the environment as well as on the global and local planners. We then propose a new adaptive replanning strategy based on deep reinforcement learning, where an agent learns from experiences to decide appropriate replanning timings in the given environment and planning setups. Our experimental results demonstrate that the proposed replanning agent can achieve performance on par or even better than current best-performing strategies across multiple situations in terms of navigation robustness and efficiency.
Many social events and policy interventions generate treatment effects that persistently spill over into neighboring areas, causing interference in both time and space. In this paper, we propose a design-based framework to identify and estimate these spillover effects in panel data, when temporal and spatial interference intertwine with each other in complex ways that are unknown to researchers. Our framework defines estimands that enable researchers to measure the influence of each type of interference, and we propose estimators that are consistent and asymptotically normal under the assumption of sequential ignorability and mild regularity conditions. We show that conventional methods in panel data analysis, such as the difference-in-differences (DID) estimator or fixed effects models, can lead to significant biases in such scenarios. We test the method's performance on both simulated datasets and the replication of an empirical study from political science.
This paper proposes a natural evolution strategy (NES) for mixed-integer black-box optimization (MI-BBO) that appears in real-world problems such as hyperparameter optimization of machine learning and materials design. This problem is difficult to optimize because plateaus where the values do not change appear when the integer variables are relaxed to the continuous ones. CMA-ES w. Margin that addresses the plateaus reportedly showed good performance on MI-BBO benchmark problems. However, it has been observed that the search performance of CMA-ES w. Margin deteriorates when continuous variables contribute more to the objective function value than integer ones. In order to address the problem of CMA-ES w. Margin, we propose Distance-weighted eXponential Natural Evolution Strategy taking account of Implicit Constraint and Integer (DX-NES-ICI). We compare the search performance of DX-NES-ICI with that of CMA-ES w. Margin through numerical experiments. As a result, DX-NES-ICI was up to 3.7 times better than CMA-ES w. Margin in terms of a rate of finding the optimal solutions on benchmark problems where continuous variables contribute more to the objective function value than integer ones. DX-NES-ICI also outperformed CMA-ES w. Margin on problems where CMA-ES w. Margin originally showed good performance.
The emergence of reinforcement learning (RL) methods in traffic signal control tasks has achieved better performance than conventional rule-based approaches. Most RL approaches require the observation of the environment for the agent to decide which action is optimal for a long-term reward. However, in real-world urban scenarios, missing observation of traffic states may frequently occur due to the lack of sensors, which makes existing RL methods inapplicable on road networks with missing observation. In this work, we aim to control the traffic signals in a real-world setting, where some of the intersections in the road network are not installed with sensors and thus with no direct observations around them. To the best of our knowledge, we are the first to use RL methods to tackle the traffic signal control problem in this real-world setting. Specifically, we propose two solutions: the first one imputes the traffic states to enable adaptive control, and the second one imputes both states and rewards to enable adaptive control and the training of RL agents. Through extensive experiments on both synthetic and real-world road network traffic, we reveal that our method outperforms conventional approaches and performs consistently with different missing rates. We also provide further investigations on how missing data influences the performance of our model.
Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to addressing this task is to build an effective class-agnostic mask segmentation model. Unlike previous methods that learn such models only on seen categories, in this paper, we propose a new method, named ContrastMask, which learns a mask segmentation model on both seen and unseen categories under a unified pixel-level contrastive learning framework. In this framework, annotated masks of seen categories and pseudo masks of unseen categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa. Through this framework, feature discrimination between foreground and background is largely improved, facilitating learning of the class-agnostic mask segmentation model. Exhaustive experiments on the COCO dataset demonstrate the superiority of our method, which outperforms previous state-of-the-arts.
Imitation learning aims to extract knowledge from human experts' demonstrations or artificially created agents in order to replicate their behaviors. Its success has been demonstrated in areas such as video games, autonomous driving, robotic simulations and object manipulation. However, this replicating process could be problematic, such as the performance is highly dependent on the demonstration quality, and most trained agents are limited to perform well in task-specific environments. In this survey, we provide a systematic review on imitation learning. We first introduce the background knowledge from development history and preliminaries, followed by presenting different taxonomies within Imitation Learning and key milestones of the field. We then detail challenges in learning strategies and present research opportunities with learning policy from suboptimal demonstration, voice instructions and other associated optimization schemes.
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the difference between the actions committed by the expert (or ground truth) and the agent among complicated states in the environment. EE task benefits from these dynamic rewards because instances and labels yield to various extents of difficulty and the gains are expected to be diverse -- e.g., an ambiguous but correctly detected trigger or argument should receive high gains -- while the traditional RL models usually neglect such differences and pay equal attention on all instances. Moreover, our experiments also demonstrate that the proposed framework outperforms state-of-the-art methods, without explicit feature engineering.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191