There exist very few ways to isolate cognitive processes, historically defined via highly controlled laboratory studies, in more ecologically valid contexts. Specifically, it remains unclear as to what extent patterns of neural activity observed under such constraints actually manifest outside the laboratory in a manner that can be used to make an accurate inference about the latent state, associated cognitive process, or proximal behavior of the individual. Improving our understanding of when and how specific patterns of neural activity manifest in ecologically valid scenarios would provide validation for laboratory-based approaches that study similar neural phenomena in isolation and meaningful insight into the latent states that occur during complex tasks. We argue that domain generalization methods from the brain-computer interface community have the potential to address this challenge. We previously used such an approach to decode phasic neural responses associated with visual target discrimination. Here, we extend that work to more tonic phenomena such as internal latent states. We use data from two highly controlled laboratory paradigms to train two separate domain-generalized models. We apply the trained models to an ecologically valid paradigm in which participants performed multiple, concurrent driving-related tasks. Using the pretrained models, we derive estimates of the underlying latent state and associated patterns of neural activity. Importantly, as the patterns of neural activity change along the axis defined by the original training data, we find changes in behavior and task performance consistent with the observations from the original, laboratory paradigms. We argue that these results lend ecological validity to those experimental designs and provide a methodology for understanding the relationship between observed neural activity and behavior during complex tasks.
While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of reward sparsity. This is especially true for tasks such as training an agent to play StarCraft II, a real-time strategy game where reward is only given at the end of a game which is usually very long. While this problem can be addressed through reward shaping, such approaches typically require a human expert with specialized knowledge. Inspired by the vision of enabling reward shaping through the more-accessible paradigm of natural-language narration, we investigate to what extent we can contextualize these narrations by grounding them to the goal-specific states. We present a mutual-embedding model using a multi-input deep-neural network that projects a sequence of natural language commands into the same high-dimensional representation space as corresponding goal states. We show that using this model we can learn an embedding space with separable and distinct clusters that accurately maps natural-language commands to corresponding game states . We also discuss how this model can allow for the use of narrations as a robust form of reward shaping to improve RL performance and efficiency.
While recent advances in deep reinforcement learning have allowed autonomous learning agents to succeed at a variety of complex tasks, existing algorithms generally require a lot of training data. One way to increase the speed at which agents are able to learn to perform tasks is by leveraging the input of human trainers. Although such input can take many forms, real-time, scalar-valued feedback is especially useful in situations where it proves difficult or impossible for humans to provide expert demonstrations. Previous approaches have shown the usefulness of human input provided in this fashion (e.g., the TAMER framework), but they have thus far not considered high-dimensional state spaces or employed the use of deep learning. In this paper, we do both: we propose Deep TAMER, an extension of the TAMER framework that leverages the representational power of deep neural networks in order to learn complex tasks in just a short amount of time with a human trainer. We demonstrate Deep TAMER's success by using it and just 15 minutes of human-provided feedback to train an agent that performs better than humans on the Atari game of Bowling - a task that has proven difficult for even state-of-the-art reinforcement learning methods.
As the technology for acquiring and storing images becomes more prevalent, we are faced with a growing need to sort and label these images. At this time, computer vision algorithms cannot parse abstract concepts from images like a human. As a result, there may be performance gains possible from the integration of human analysts with computer vision agents. We present an image triage system which facilitates the collaboration of heterogeneous agents through a novel unsupervised meta-learning technique. The system iteratively allocates images for binary classification among heterogeneous agents according to the Generalized Assignment Problem (GAP) and combines the classification results using the Spectral Meta-Learner (SML). In simulation, we demonstrate that the proposed system achieves significant speed-up over a naive parallel assignment strategy without sacrificing accuracy.
The application of Artificial Intelligence and Machine Learning (AI/ML) technologies to Aided Target Recognition (AiTR) systems will significantly improve target acquisition and engagement effectiveness. Although, the effectiveness of these AI/ML technologies is based on the quantity and quality of labeled training data, there is very limited labeled operational data available. Creating this data is both time-consuming and expensive, and AI/ML technologies can be brittle and unable to adapt to changing environmental conditions or adversary tactics that are not represented in the training data. As a result, continuous operational data collection and labeling are required to adapt and refine these algorithms, but collecting and labeling operational data carries potentially catastrophic risks if it requires Soldier interaction that degrades critical task performance. Addressing this problem to achieve robust, effective AI/ML for AiTR requires a multi-faceted approach integrating a variety of techniques such as generating synthetic data and using algorithms that learn on sparse and incomplete data. In particular, we argue that it is critical to leverage opportunistic sensing: obtaining operational data required to train and validate AI/ML algorithms from tasks the operator is already doing, without negatively affecting performance on those tasks or requiring any additional tasks to be performed. By leveraging the Soldier's substantial skills, capabilities, and adaptability, it will be possible to develop effective and adaptive AI/ML technologies for AiTR in the future Multi- Domain Operations (MDO) battlefield.
This paper investigates how to efficiently transition and update policies, trained initially with demonstrations, using off-policy actor-critic reinforcement learning. It is well-known that techniques based on Learning from Demonstrations, for example behavior cloning, can lead to proficient policies given limited data. However, it is currently unclear how to efficiently update that policy using reinforcement learning as these approaches are inherently optimizing different objective functions. Previous works have used loss functions, which combine behavior cloning losses with reinforcement learning losses to enable this update. However, the components of these loss functions are often set anecdotally, and their individual contributions are not well understood. In this work, we propose the Cycle-of-Learning (CoL) framework that uses an actor-critic architecture with a loss function that combines behavior cloning and 1-step Q-learning losses with an off-policy pre-training step from human demonstrations. This enables transition from behavior cloning to reinforcement learning without performance degradation and improves reinforcement learning in terms of overall performance and training time. Additionally, we carefully study the composition of these combined losses and their impact on overall policy learning. We show that our approach outperforms state-of-the-art techniques for combining behavior cloning and reinforcement learning for both dense and sparse reward scenarios. Our results also suggest that directly including the behavior cloning loss on demonstration data helps to ensure stable learning and ground future policy updates.
This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions. We implement two components of the Cycle-of-Learning for Autonomous Systems, which is our framework for combining multiple modalities of human interaction. The current effort employs human demonstrations to teach a desired behavior via imitation learning, then leverages intervention data to correct for undesired behaviors produced by the imitation learner to teach novel tasks to an autonomous agent safely, after only minutes of training. We demonstrate this method in an autonomous perching task using a quadrotor with continuous roll, pitch, yaw, and throttle commands and imagery captured from a downward-facing camera in a high-fidelity simulated environment. Our method improves task completion performance for the same amount of human interaction when compared to learning from demonstrations alone, while also requiring on average 32% less data to achieve that performance. This provides evidence that combining multiple modes of human interaction can increase both the training speed and overall performance of policies for autonomous systems.
This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions. We implement two components of the Cycle-of-Learning for Autonomous Systems, which is our framework for combining multiple modalities of human interaction. The current effort employs human demonstrations to teach a desired behavior via imitation learning, then leverages intervention data to correct for undesired behaviors produced by the imitation learner to teach novel tasks to an autonomous agent safely, after only minutes of training. We demonstrate this method in an autonomous perching task using a quadrotor with continuous roll, pitch, yaw, and throttle commands and imagery captured from a downward-facing camera in a high-fidelity simulated environment. Our method improves task completion performance for the same amount of human interaction when compared to learning from demonstrations alone, while also requiring on average 32% less data to achieve that performance. This provides evidence that combining multiple modes of human interaction can increase both the training speed and overall performance of policies for autonomous systems.
The papers in this special section focus on brain computer interfaces. A brain computer interface (BCI) enables direct communication between the brain and a computer. It can be used to research, repair, or enhance human cognitive or sensorymotor functions. BCIs have attracted rapidly increasing research interest in the last decade, thanks to recent advances in neurosciences, wearable/mobile biosensors, and analytics. However, there are many challenges in the transition from laboratory settings to real-life applications, including the reliability and convenience of the sensing hardware, the availability of high performance and robust algorithms for signal analysis and interpretation, and fundamental advances in automated reasoning that enable the reasoning and generalization across individuals. Computational intelligence techniques, particularly fuzzy sets and systems, have demonstrated outstanding performance in handling uncertainties in many real-world applications.
We discuss different types of human-robot interaction paradigms in the context of training end-to-end reinforcement learning algorithms. We provide a taxonomy to categorize the types of human interaction and present our Cycle-of-Learning framework for autonomous systems that combines different human-interaction modalities with reinforcement learning. Two key concepts provided by our Cycle-of-Learning framework are how it handles the integration of the different human-interaction modalities (demonstration, intervention, and evaluation) and how to define the switching criteria between them.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)