We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC) that adopts supervised learning followed by the problem of compounding error, previous solutions like inverse reinforcement learning (IRL) and recent generative adversarial methods involve a bi-level or alternating optimization for updating the reward function and the policy, suffering from high computational cost and training instability. Inspired by recent progress in energy-based model (EBM), in this paper, we propose a simplified IL framework named Energy-Based Imitation Learning (EBIL). Instead of updating the reward and policy iteratively, EBIL breaks out of the traditional IRL paradigm by a simple and flexible two-stage solution: first estimating the expert energy as the surrogate reward function through score matching, then utilizing such a reward for learning the policy by reinforcement learning algorithms. EBIL combines the idea of both EBM and occupancy measure matching, and via theoretic analysis we reveal that EBIL and Max-Entropy IRL (MaxEnt IRL) approaches are two sides of the same coin, and thus EBIL could be an alternative of adversarial IRL methods. Extensive experiments on qualitative and quantitative evaluations indicate that EBIL is able to recover meaningful and interpretative reward signals while achieving effective and comparable performance against existing algorithms on IL benchmarks.

0
下载
关闭预览

相关内容

iOS 8 提供的应用间和应用跟系统的功能交互特性。
  • Today (iOS and OS X): widgets for the Today view of Notification Center
  • Share (iOS and OS X): post content to web services or share content with others
  • Actions (iOS and OS X): app extensions to view or manipulate inside another app
  • Photo Editing (iOS): edit a photo or video in Apple's Photos app with extensions from a third-party apps
  • Finder Sync (OS X): remote file storage in the Finder with support for Finder content annotation
  • Storage Provider (iOS): an interface between files inside an app and other apps on a user's device
  • Custom Keyboard (iOS): system-wide alternative keyboards

Source: iOS 8 Extensions: Apple’s Plan for a Powerful App Ecosystem

A self-learning adaptive system (SLAS) uses machine learning to enable and enhance its adaptability. Such systems are expected to perform well in dynamic situations. For learning high-performance adaptation policy, some assumptions must be made on the environment-system dynamics when information about the real situation is incomplete. However, these assumptions cannot be expected to be always correct, and yet it is difficult to enumerate all possible assumptions. This leads to the problem of incomplete-information learning. We consider this problem as multiple model problem in terms of finding the adaptation policy that can cope with multiple models of environment-system dynamics. This paper proposes a novel approach to engineering the online adaptation of SLAS. It separates three concerns that are related to the adaptation policy and presents the modeling and synthesis process, with the goal of achieving higher model construction efficiency. In addition, it designs a meta-reinforcement learning algorithm for learning the meta policy over the multiple models, so that the meta policy can quickly adapt to the real environment-system dynamics. At last, it reports the case study on a robotic system to evaluate the adaptability of the approach.

0
0
下载
预览

Recommender systems rely on user behavior data like ratings and clicks to build personalization model. However, the collected data is observational rather than experimental, causing various biases in the data which significantly affect the learned model. Most existing work for recommendation debiasing, such as the inverse propensity scoring and imputation approaches, focuses on one or two specific biases, lacking the universal capacity that can account for mixed or even unknown biases in the data. Towards this research gap, we first analyze the origin of biases from the perspective of \textit{risk discrepancy} that represents the difference between the expectation empirical risk and the true risk. Remarkably, we derive a general learning framework that well summarizes most existing debiasing strategies by specifying some parameters of the general framework. This provides a valuable opportunity to develop a universal solution for debiasing, e.g., by learning the debiasing parameters from data. However, the training data lacks important signal of how the data is biased and what the unbiased data looks like. To move this idea forward, we propose \textit{AotoDebias} that leverages another (small) set of uniform data to optimize the debiasing parameters by solving the bi-level optimization problem with meta-learning. Through theoretical analyses, we derive the generalization bound for AutoDebias and prove its ability to acquire the appropriate debiasing strategy. Extensive experiments on two real datasets and a simulated dataset demonstrated effectiveness of AutoDebias. The code is available at \url{https://github.com/DongHande/AutoDebias}.

0
0
下载
预览

This brief sketches initial progress towards a unified energy-based solution for the semi-supervised visual anomaly detection and localization problem. In this setup, we have access to only anomaly-free training data and want to detect and identify anomalies of an arbitrary nature on test data. We employ the density estimates from the energy-based model (EBM) as normalcy scores that can be used to discriminate normal images from anomalous ones. Further, we back-propagate the gradients of the energy score with respect to the image in order to generate a gradient map that provides pixel-level spatial localization of the anomalies in the image. In addition to the spatial localization, we show that simple processing of the gradient map can also provide alternative normalcy scores that either match or surpass the detection performance obtained with the energy value. To quantitatively validate the performance of the proposed method, we conduct experiments on the MVTec industrial dataset. Though still preliminary, our results are very promising and reveal the potential of EBMs for simultaneously detecting and localizing unforeseen anomalies in images.

0
0
下载
预览

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the training task distribution, the performance may degrade significantly. To address this issue, this paper proposes Model-based Adversarial Meta-Reinforcement Learning (AdMRL), where we aim to minimize the worst-case sub-optimality gap -- the difference between the optimal return and the return that the algorithm achieves after adaptation -- across all tasks in a family of tasks, with a model-based approach. We propose a minimax objective and optimize it by alternating between learning the dynamics model on a fixed task and finding the adversarial task for the current model -- the task for which the policy induced by the model is maximally suboptimal. Assuming the family of tasks is parameterized, we derive a formula for the gradient of the suboptimality with respect to the task parameters via the implicit function theorem, and show how the gradient estimator can be efficiently implemented by the conjugate gradient method and a novel use of the REINFORCE estimator. We evaluate our approach on several continuous control benchmarks and demonstrate its efficacy in the worst-case performance over all tasks, the generalization power to out-of-distribution tasks, and in training and test time sample efficiency, over existing state-of-the-art meta-RL algorithms.

0
3
下载
预览

Fashion is a complex social phenomenon. People follow fashion styles from demonstrations by experts or fashion icons. However, for machine agent, learning to imitate fashion experts from demonstrations can be challenging, especially for complex styles in environments with high-dimensional, multimodal observations. Most existing research regarding fashion outfit composition utilizes supervised learning methods to mimic the behaviors of style icons. These methods suffer from distribution shift: because the agent greedily imitates some given outfit demonstrations, it can drift away from one style to another styles given subtle differences. In this work, we propose an adversarial inverse reinforcement learning formulation to recover reward functions based on hierarchical multimodal representation (HM-AIRL) during the imitation process. The hierarchical joint representation can more comprehensively model the expert composited outfit demonstrations to recover the reward function. We demonstrate that the proposed HM-AIRL model is able to recover reward functions that are robust to changes in multimodal observations, enabling us to learn policies under significant variation between different styles.

0
7
下载
预览

Deep Learning is applied to energy markets to predict extreme loads observed in energy grids. Forecasting energy loads and prices is challenging due to sharp peaks and troughs that arise due to supply and demand fluctuations from intraday system constraints. We propose deep spatio-temporal models and extreme value theory (EVT) to capture theses effects and in particular the tail behavior of load spikes. Deep LSTM architectures with ReLU and $\tanh$ activation functions can model trends and temporal dependencies while EVT captures highly volatile load spikes above a pre-specified threshold. To illustrate our methodology, we use hourly price and demand data from 4719 nodes of the PJM interconnection, and we construct a deep predictor. We show that DL-EVT outperforms traditional Fourier time series methods, both in-and out-of-sample, by capturing the observed nonlinearities in prices. Finally, we conclude with directions for future research.

0
4
下载
预览

Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learning algorithm. The advantage is that the algorithm can then use the reward function to check the reward for states that the agent hasn't even encountered yet. In addition, the algorithm can simultaneously learn policies for multiple reward functions. For each state, the algorithm would calculate the reward using each of the reward functions and add the rewards to its experience replay dataset. The Hindsight Experience Replay algorithm developed by Andrychowicz et al. (2017) does just this, and learns to generalize across a distribution of sparse, goal-based rewards. We extend this algorithm to linearly-weighted, multi-objective rewards and learn a single policy that can generalize across all linear combinations of the multi-objective reward. Whereas other multi-objective algorithms teach the Q-function to generalize across the reward weights, our algorithm enables the policy to generalize, and can thus be used with continuous actions.

0
5
下载
预览

Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the pre-processing perception system while the supervised learning-based models are limited by the accessibility of extensive human experience. We present a general and principled Controllable Imitative Reinforcement Learning (CIRL) approach which successfully makes the driving agent achieve higher success rates based on only vision inputs in a high-fidelity car simulator. To alleviate the low exploration efficiency for large continuous action space that often prohibits the use of classical RL on challenging real tasks, our CIRL explores over a reasonably constrained action space guided by encoded experiences that imitate human demonstrations, building upon Deep Deterministic Policy Gradient (DDPG). Moreover, we propose to specialize adaptive policies and steering-angle reward designs for different control signals (i.e. follow, straight, turn right, turn left) based on the shared representations to improve the model capability in tackling with diverse cases. Extensive experiments on CARLA driving benchmark demonstrate that CIRL substantially outperforms all previous methods in terms of the percentage of successfully completed episodes on a variety of goal-directed driving tasks. We also show its superior generalization capability in unseen environments. To our knowledge, this is the first successful case of the learned driving policy through reinforcement learning in the high-fidelity simulator, which performs better-than supervised imitation learning.

0
4
下载
预览

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.

0
13
下载
预览

Despite of the success of Generative Adversarial Networks (GANs) for image generation tasks, the trade-off between image diversity and visual quality are an well-known issue. Conventional techniques achieve either visual quality or image diversity; the improvement in one side is often the result of sacrificing the degradation in the other side. In this paper, we aim to achieve both simultaneously by improving the stability of training GANs. A key idea of the proposed approach is to implicitly regularizing the discriminator using a representative feature. For that, this representative feature is extracted from the data distribution, and then transferred to the discriminator for enforcing slow updates of the gradient. Consequently, the entire training process is stabilized because the learning curve of discriminator varies slowly. Based on extensive evaluation, we demonstrate that our approach improves the visual quality and diversity of state-of-the art GANs.

0
7
下载
预览
小贴士
相关论文
Mingyue Zhang,Jialong Li,Haiyan Zhao,Kenji Tei,Shinichi Honiden,Zhi Jin
0+阅读 · 5月11日
Jiawei Chen,Hande Dong,Yang Qiu,Xiangnan He,Xin Xin,Liang Chen,Guli Lin,Keping Yang
0+阅读 · 5月10日
Ergin Utku Genc,Nilesh Ahuja,Ibrahima J Ndiour,Omesh Tickoo
0+阅读 · 5月7日
Zichuan Lin,Garrett Thomas,Guangwen Yang,Tengyu Ma
3+阅读 · 2020年6月16日
Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation
Shizhu Liu,Shanglin Yang,Hui Zhou
7+阅读 · 2020年4月13日
Deep Learning for Energy Markets
Michael Polson,Vadim Sokolov
4+阅读 · 2019年4月10日
Generalizing Across Multi-Objective Reward Functions in Deep Reinforcement Learning
Eli Friedman,Fred Fontaine
5+阅读 · 2018年9月17日
CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving
Xiaodan Liang,Tairui Wang,Luona Yang,Eric Xing
4+阅读 · 2018年7月10日
Tongtao Zhang,Heng Ji
13+阅读 · 2018年4月21日
Duhyeon Bang,Hyunjung Shim
7+阅读 · 2018年1月28日
相关资讯
强化学习三篇论文 避免遗忘等
CreateAMind
11+阅读 · 2019年5月24日
Transferring Knowledge across Learning Processes
CreateAMind
6+阅读 · 2019年5月18日
动物脑的好奇心和强化学习的好奇心
CreateAMind
6+阅读 · 2019年1月26日
逆强化学习-学习人先验的动机
CreateAMind
5+阅读 · 2019年1月18日
强化学习的Unsupervised Meta-Learning
CreateAMind
7+阅读 · 2019年1月7日
Unsupervised Learning via Meta-Learning
CreateAMind
26+阅读 · 2019年1月3日
meta learning 17年:MAML SNAIL
CreateAMind
8+阅读 · 2019年1月2日
Hierarchical Imitation - Reinforcement Learning
CreateAMind
15+阅读 · 2018年5月25日
强化学习族谱
CreateAMind
10+阅读 · 2017年8月2日
强化学习 cartpole_a3c
CreateAMind
9+阅读 · 2017年7月21日
Top