Stone, Peter

Robot Representing and Reasoning with Knowledge from Reinforcement Learning Artificial Intelligence

Reinforcement learning (RL) agents aim at learning by interacting with an environment, and are not designed for representing or reasoning with declarative knowledge. Knowledge representation and reasoning (KRR) paradigms are strong in declarative KRR tasks, but are ill-equipped to learn from such experiences. In this work, we integrate logical-probabilistic KRR with model-based RL, enabling agents to simultaneously reason with declarative knowledge and learn from interaction experiences. The knowledge from humans and RL is unified and used for dynamically computing task-specific planning models under potentially new environments. Experiments were conducted using a mobile robot working on dialog, navigation, and delivery tasks. Results show significant improvements, in comparison to existing model-based RL methods.

Deterministic Implementations for Reproducibility in Deep Reinforcement Learning Artificial Intelligence

While deep reinforcement learning (DRL) has led to numerous successes in recent years, reproducing these successes can be extremely challenging. One reproducibility challenge particularly relevant to DRL is nondeterminism in the training process, which can substantially affect the results. Motivated by this challenge, we study the positive impacts of deterministic implementations in eliminating nondeterminism in training. To do so, we consider the particular case of the deep Q-learning algorithm, for which we produce a deterministic implementation by identifying and controlling all sources of nondeterminism in the training process. One by one, we then allow individual sources of nondeterminism to affect our otherwise deterministic implementation, and measure the impact of each source on the variance in performance. We find that individual sources of nondeterminism can substantially impact the performance of agent, illustrating the benefits of deterministic implementations. In addition, we also discuss the important role of deterministic implementations in achieving exact replicability of results.

Learning a Policy for Opportunistic Active Learning Artificial Intelligence

Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.

A Century Long Commitment to Assessing Artificial Intelligence and its Impact on Society Artificial Intelligence

In September 2016, Stanford's "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the first report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society. The report, entitled "Artificial Intelligence and Life in 2030," examines eight domains of typical urban settings on which AI is likely to have impact over the coming years: transportation, home and service robots, healthcare, education, public safety and security, low-resource communities, employment and workplace, and entertainment. It aims to provide the general public with a scientifically and technologically accurate portrayal of the current state of AI and its potential and to help guide decisions in industry and governments, as well as to inform research and development in the field. This article by the chair of the 2016 Study Panel and the inaugural chair of the AI100 Standing Committee describes the origins of this ambitious longitudinal study, discusses the framing of the inaugural report, and presents the report's main findings. It concludes with a brief description of the AI100 project's ongoing efforts and planned next steps.

Generative Adversarial Imitation from Observation Artificial Intelligence

Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions. The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to learn from large set of previously inapplicable resources such as internet videos. In this paper, we propose both a general framework for IfO approaches and propose a new IfO approach based on generative adversarial networks called generative adversarial imitation from observation (GAIfO). We demonstrate that this approach performs comparably to classical imitation learning approaches (which have access to the demonstrator's actions) and significantly outperforms existing imitation from observation methods in high-dimensional simulation environments.

Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science Artificial Intelligence

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general practice) artificial neural networks, too, should not have fully-connected layers. Here we propose sparse evolutionary training of artificial neural networks, an algorithm which evolves an initial sparse topology (Erd\H{o}s-R\'enyi random graph) of two consecutive layers of neurons into a scale-free topology, during learning. Our method replaces artificial neural networks fully-connected layers with sparse ones before training, reducing quadratically the number of parameters, with no decrease in accuracy. We demonstrate our claims on restricted Boltzmann machines, multi-layer perceptrons, and convolutional neural networks for unsupervised and supervised learning on 15 datasets. Our approach has the potential to enable artificial neural networks to scale up beyond what is currently possible.

Importance Sampling Policy Evaluation with an Estimated Behavior Policy Machine Learning

In reinforcement learning, off-policy evaluation is the task of using data generated by one policy to determine the expected return of a second policy. Importance sampling is a standard technique for off-policy evaluation, allowing off-policy data to be used as if it were on-policy. When the policy that generated the off-policy data is unknown, the ordinary importance sampling estimator cannot be applied. In this paper, we study a family of regression importance sampling (RIS) methods that apply importance sampling by first estimating the behavior policy. We find that these estimators give strong empirical performance---surprisingly often outperforming importance sampling with the true behavior policy in both discrete and continuous domains. Our results emphasize the importance of estimating the behavior policy using only the data that will also be used for the importance sampling estimate.

Behavioral Cloning from Observation Artificial Intelligence

Humans often learn how to perform tasks via imitation: they observe others perform a task, and then very quickly infer the appropriate actions to take based on their observations. While extending this paradigm to autonomous agents is a well-studied problem in general, there are two particular aspects that have largely been overlooked: (1) that the learning is done from observation only (i.e., without explicit action information), and (2) that the learning is typically done very quickly. In this work, we propose a two-phase, autonomous imitation learning technique called behavioral cloning from observation (BCO), that aims to provide improved performance with respect to both of these aspects. First, we allow the agent to acquire experience in a self-supervised fashion. This experience is used to develop a model which is then utilized to learn a particular task by observing an expert perform that task without the knowledge of the specific actions taken. We experimentally compare BCO to imitation learning methods, including the state-of-the-art, generative adversarial imitation learning (GAIL) technique, and we show comparable task performance in several different simulation domains while exhibiting increased learning speed after expert trajectories become available.

An Empirical Comparison of PDDL-based and ASP-based Task Planners Artificial Intelligence

General purpose planners enable AI systems to solve many different types of planning problems. However, many different planners exist, each with different strengths and weaknesses, and there are no general rules for which planner would be best to apply to a given problem. In this paper, we empirically compare the performance of state-of-the-art planners that use either the Planning Domain Description Language (PDDL), or Answer Set Programming (ASP) as the underlying action language. PDDL is designed for automated planning, and PDDL-based planners are widely used for a variety of planning problems. ASP is designed for knowledge-intensive reasoning, but can also be used for solving planning problems. Given domain encodings that are as similar as possible, we find that PDDL-based planners perform better on problems with longer solutions, and ASP-based planners are better on tasks with a large number of objects or in which complex reasoning is required to reason about action preconditions and effects. The resulting analysis can inform selection among general purpose planning systems for a particular domain.

Autonomous Model Management via Reinforcement Learning

AAAI Conferences

Concept drift - a change, either sudden or gradual, in the underlying properties of data - is one of the most prevalent challenges to maintaining high-performing learned models over time in autonomous systems. In the face of concept drift, one can hope that the old model is sufficiently representative of the new data despite the concept drift, one can discard the old data and retrain a new model with (often limited) new data, or one can use transfer learning methods to combine the old data with the new to create an updated model. Which of these three options is chosen affects not only near-term decisions, but also future needs to transfer or retrain. In this paper, we thus model response to concept drift as a sequential decision making problem and formally frame it as a Markov Decision Process. Our reinforcement learning approach to the problem shows promising results on one synthetic and two real-world datasets.