Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract...
详细信息
Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) diverse state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive behaviors based on their resultant states - a more informative criterion enabling explicit utilization of dynamics information and effective extraction of both expert and beneficial diverse behaviors. Further, we devise a lightweight behavior cloning algorithm capable of leveraging the expert and selected data correctly. In the experiments, we evaluate our method on a suite of complex and high-dimensional offline IL benchmarks, including continuous-control and vision-based tasks. The results demonstrate that our method achieves state-of-the-art performance, outperforming existing methods on 20/21 benchmarks, typically by 2-5x, while maintaining a comparable runtime to Behavior Cloning (BC). Copyright 2024 by the author(s)
作者：
Hannah Jessie Rani, R.Rajat, Rajat
Department of Electrical and Electronics Engineering Bangalore India
Department of Computer Science and Engineering Bangalore India
The Smart Transmitter (ST) parameter estimate presents a particular problem in Mobile Ad Hoc Networks (MANETs). Nodes in these networks must develop the ability to adapt to their dynamic environment, which includes el...
详细信息
We have developed HEARTS, a dementia care training system using augmented reality based on Humanitude. Humanitude is a multimodal comprehensive care technique for dementia, and has attracted attention as a method to r...
详细信息
The conventional paradigm of communication primarily concentrates on the transmission of raw data, often disregarding its contextual meaning. However, to tackle the exponential growth in data demands along with the li...
详细信息
The Supreme Court plays an extremely critical role in ensuring adherence to the rule of law and in strengthening the democracy. Due to this reason, modeling and analysis of small group interactions in t...
详细信息
For communications subject to correlated channel effects, noise recycling has recently been shown to enhance channel capacity with receiver-side-only changes. Using a taped-out chip, in a hard-detection scenario with ...
详细信息
With the rapid proliferation of mobile devices, the marriage of millimeter-wave (mmWave) and MIMO technologies is a natural trend to meet the communication demand of data-hungry applications. Following this trend, mmW...
详细信息
As artificial intelligence and big data become increasingly prevalent,resistive random-access memory(RRAM)has become one of the most promising alternatives for storing massive amounts of *** this study,we employed hig...
详细信息
As artificial intelligence and big data become increasingly prevalent,resistive random-access memory(RRAM)has become one of the most promising alternatives for storing massive amounts of *** this study,we employed high-quality crystalline TiN/Al2O3/BaTiO3/Pt RRAM with an optimized thin Al2O3 in-terlayer around 12 nm thick prepared using atomic layer deposition since the thickness of the inter-layer affects the memory window *** insertion of the Al2O3 interlayer,the novel RRAM exhibited outstanding uniform resistive switching voltage and the ON/OFF memory window drastically increased from 10 to 103 without any discernible decline in ***,the low-resistance state and high-resistance state operating current values decreased by almost one order and three orders of magni-tude,respectively,thereby decreasing the power consumption for the RESET and SET processes by more than three and almost one order of magnitude,*** device also exhibits multilevel resistive switching behavior when varying the applied ***,we also developed a 6 × 6 crossbar array which demonstrated consistent and reliable resistive switching behavior with minimal ***,our approach holds great promise for producing state-of-the-art non-volatile resistive switching devices.
Wireless charging is a promising solution for charging battery-driven devices pervasively. However, the wide deployment of wireless charging stations is vulnerable to the device masquerade attack, which causes financi...
详细信息
In this study, we propose a new deep convolutional generative adversarial kinematics network (DCGAKN) to establish inverse kinematics of self-assembly robotic arm. We design that the robot system uses a depth sensor d...
详细信息
暂无评论