As data collection is often significantly cheaper than labeling in this domain, the decision of which subset of examples to label can have a profound impact on model performance.
Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems.
Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters.
Importantly, by simulating directly from sensor data, we obtain adversarial scenarios that are safety-critical for the full autonomy stack.
Learned communication makes multi-agent systems more effective by aggregating distributed information.
Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).
Although recent works have shown the benefits of instructive texts in goal-conditioned RL, few have studied whether descriptive texts help agents to generalize across dynamic environments.
The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing adversarial robustness against norm-ball bounded input perturbations.
In this paper, we show how a general framework of min-max optimization over multiple domains can be leveraged to advance the design of different types of adversarial attacks.
Despite the great success achieved in machine learning (ML), adversarial examples have caused concerns with regards to its trustworthiness: A small perturbation of an input results in an arbitrary failure of an otherwise seemingly well-trained ML model.
For instance, the state-of-the-art PPO algorithm is able to obtain 84. 6% and 80. 8% improvements on average score for five Atari games, with error rates as 10% and 30% respectively.
Chinese word segmentation (CWS) is often regarded as a character-based sequence labeling task in most current works which have achieved great success with the help of powerful neural networks.
This paper proposes a fundamental answer to a frequently asked question in multimedia computing and machine learning: Do artifacts from perceptual compression contribute to error in the machine learning process and if so, how much?
Learning autonomous-driving policies is one of the most challenging but promising tasks for computer vision.