13 citations · 53 across the 11 of their papers we have counts for
14 papers
Shaping Advice in Deep Reinforcement Learning
Baicen Xiao, Bhaskar Ramasubramanian, Radha Poovendran
Reinforcement learning involves agents interacting with an environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feed…
Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning
Baicen Xiao, Bhaskar Ramasubramanian, Radha Poovendran
This paper considers multi-agent reinforcement learning (MARL) tasks where agents receive a shared global reward at the end of an episode. The delayed nature of this reward affects…
Shaping Advice in Deep Multi-Agent Reinforcement Learning
Baicen Xiao, Bhaskar Ramasubramanian, Radha Poovendran
Multi-agent reinforcement learning involves multiple agents interacting with each other and a shared environment to complete tasks. When rewards provided by the environment are spa…
Safety-Critical Online Control with Adversarial Disturbances
Bhaskar Ramasubramanian, Baicen Xiao, Linda Bushnell +1
This paper studies the control of safety-critical dynamical systems in the presence of adversarial disturbances. We seek to synthesize state-feedback controllers to minimize a cost…
FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback
Baicen Xiao, Qifan Lu, Bhaskar Ramasubramanian +3
Reinforcement learning has been successful in training autonomous agents to accomplish goals in complex environments. Although this has been adapted to multiple settings, including…
Potential-Based Advice for Stochastic Policy Learning
Baicen Xiao, Bhaskar Ramasubramanian, Andrew Clark +3
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show…
Assessing Shape Bias Property of Convolutional Neural Networks
Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal +1
It is known that humans display "shape bias" when classifying new items, i.e., they prefer to categorize objects based on their shape rather than color. Convolutional Neural Networ…
Attacking Automatic Video Analysis Algorithms: A Case Study of Google Cloud Video Intelligence API
Hossein Hosseini, Baicen Xiao, Andrew Clark +1
Due to the growth of video data on Internet, automatic video analysis has gained a lot of attention from academia as well as companies such as Facebook, Twitter and Google. In this…
Google's Cloud Vision API Is Not Robust To Noise
Hossein Hosseini, Baicen Xiao, Radha Poovendran
Google has recently introduced the Cloud Vision API for image analysis. According to the demonstration website, the API "quickly classifies images into thousands of categories, det…
Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos
Hossein Hosseini, Baicen Xiao, Radha Poovendran
Despite the rapid progress of the techniques for image classification, video annotation has remained a challenging task. Automated video annotation would be a breakthrough technolo…
On the Limitation of Convolutional Neural Networks in Recognizing Negative Images
Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal +1
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance on a variety of computer vision tasks, particularly visual classification problems, where new algori…
On Optimizing Hierarchical Modulation in AWGN channel
Baicen Xiao, Kexin Xiao, Zhiyong Chen +1
Hierarchical modulation (HM) is able to provide different levels of protection for data streams and achieve a rate region that cannot be realized by traditional orthogonal schemes,…
Iterative detection and decoding for SCMA systems with LDPC codes
Baicen Xiao, Kexin Xiao, Shutian Zhang +3
Sparse code multiple access (SCMA) is a promising multiplexing approach to achieve high system capacity. In this paper, we develop a novel iterative detection and decoding scheme f…
Simplified Multiuser Detection for SCMA with Sum-Product Algorithm
Kexin Xiao, Baicen Xiao, Shutian Zhang +2
Sparse code multiple access (SCMA) is a novel non-orthogonal multiple access technique, which fully exploits the shaping gain of multi-dimensional codewords. However, the lack of s…