Today's robots are increasingly interacting with people and need to efficiently learn inexperienced user's preferences. A common framework is to iteratively query the user about which of two presented robot trajectories they prefer. While this minimizes the users effort, a strict choice does not yield any information on how much one trajectory is preferred. We propose scale feedback, where the user utilizes a slider to give more nuanced information. We introduce a probabilistic model on how users would provide feedback and derive a learning framework for the robot. We demonstrate the performance benefit of slider feedback in simulations, and validate our approach in two user studies suggesting that scale feedback enables more effective learning in practice.
Learning from human feedback has shown to be a useful approach in acquiring robot reward functions. However, expert feedback is often assumed to be drawn from an underlying unimodal reward function. This assumption does not always hold including in settings where multiple experts provide data or when a single expert provides data for different tasks -- we thus go beyond learning a unimodal reward and focus on learning a multimodal reward function. We formulate the multimodal reward learning as a mixture learning problem and develop a novel ranking-based learning approach, where the experts are only required to rank a given set of trajectories. Furthermore, as access to interaction data is often expensive in robotics, we develop an active querying approach to accelerate the learning process. We conduct experiments and user studies using a multi-task variant of OpenAI's LunarLander and a real Fetch robot, where we collect data from multiple users with different preferences. The results suggest that our approach can efficiently learn multimodal reward functions, and improve data-efficiency over benchmark methods that we adapt to our learning problem.
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.
Reward learning is a fundamental problem in robotics to have robots that operate in alignment with what their human user wants. Many preference-based learning algorithms and active querying techniques have been proposed as a solution to this problem. In this paper, we present APReL, a library for active preference-based reward learning algorithms, which enable researchers and practitioners to experiment with the existing techniques and easily develop their own algorithms for various modules of the problem.
Despite the advances in the autonomous driving domain, autonomous vehicles (AVs) are still inefficient and limited in terms of cooperating with each other or coordinating with vehicles operated by humans. A group of autonomous and human-driven vehicles (HVs) which work together to optimize an altruistic social utility -- as opposed to the egoistic individual utility -- can co-exist seamlessly and assure safety and efficiency on the road. Achieving this mission without explicit coordination among agents is challenging, mainly due to the difficulty of predicting the behavior of humans with heterogeneous preferences in mixed-autonomy environments. Formally, we model an AV's maneuver planning in mixed-autonomy traffic as a partially-observable stochastic game and attempt to derive optimal policies that lead to socially-desirable outcomes using a multi-agent reinforcement learning framework. We introduce a quantitative representation of the AVs' social preferences and design a distributed reward structure that induces altruism into their decision making process. Our altruistic AVs are able to form alliances, guide the traffic, and affect the behavior of the HVs to handle competitive driving scenarios. As a case study, we compare egoistic AVs to our altruistic autonomous agents in a highway merging setting and demonstrate the emerging behaviors that lead to a noticeable improvement in the number of successful merges as well as the overall traffic flow and safety.
With the adoption of autonomous vehicles on our roads, we will witness a mixed-autonomy environment where autonomous and human-driven vehicles must learn to co-exist by sharing the same road infrastructure. To attain socially-desirable behaviors, autonomous vehicles must be instructed to consider the utility of other vehicles around them in their decision-making process. Particularly, we study the maneuver planning problem for autonomous vehicles and investigate how a decentralized reward structure can induce altruism in their behavior and incentivize them to account for the interest of other autonomous and human-driven vehicles. This is a challenging problem due to the ambiguity of a human driver's willingness to cooperate with an autonomous vehicle. Thus, in contrast with the existing works which rely on behavior models of human drivers, we take an end-to-end approach and let the autonomous agents to implicitly learn the decision-making process of human drivers only from experience. We introduce a multi-agent variant of the synchronous Advantage Actor-Critic (A2C) algorithm and train agents that coordinate with each other and can affect the behavior of human drivers to improve traffic flow and safety.
Assistive robot arms enable people with disabilities to conduct everyday tasks on their own. These arms are dexterous and high-dimensional; however, the interfaces people must use to control their robots are low-dimensional. Consider teleoperating a 7-DoF robot arm with a 2-DoF joystick. The robot is helping you eat dinner, and currently you want to cut a piece of tofu. Today's robots assume a pre-defined mapping between joystick inputs and robot actions: in one mode the joystick controls the robot's motion in the x-y plane, in another mode the joystick controls the robot's z-yaw motion, and so on. But this mapping misses out on the task you are trying to perform! Ideally, one joystick axis should control how the robot stabs the tofu and the other axis should control different cutting motions. Our insight is that we can achieve intuitive, user-friendly control of assistive robots by embedding the robot's high-dimensional actions into low-dimensional and human-controllable latent actions. We divide this process into three parts. First, we explore models for learning latent actions from offline task demonstrations, and formalize the properties that latent actions should satisfy. Next, we combine learned latent actions with autonomous robot assistance to help the user reach and maintain their high-level goals. Finally, we learn a personalized alignment model between joystick inputs and latent actions. We evaluate our resulting approach in four user studies where non-disabled participants reach marshmallows, cook apple pie, cut tofu, and assemble dessert. We then test our approach with two disabled adults who leverage assistive devices on a daily basis.
Despite the leaps in the autonomous driving domain, autonomous vehicles (AVs) are still inefficient and limited in terms of cooperating with each other or coordinating with vehicles operated by humans. A group of autonomous and human-driven vehicles (HVs) which work together to optimize an altruistic social utility -- as opposed to the egoistic individual utility -- can co-exist seamlessly and assure safety and efficiency on the road. Achieving this mission is challenging in the absence of explicit coordination among agents. Additionally, existence of humans in mixed-autonomy environments create social dilemmas as they are known to be heterogeneous in social preference and their behavior is hard to predict by nature. Formally, we model an AV's maneuver planning in mixed-autonomy traffic as a partially-observable stochastic game and attempt to derive optimal policies that lead to socially-desirable outcomes using our multi-agent reinforcement learning framework. We introduce a quantitative representation of the AVs' social value orientation and design a distributed reward structure that induces altruism into their decision making process. Our trained altruistic AVs are able to form alliances, guide the traffic, and affect the behavior of the HVs to handle conflictive and competitive driving scenarios. As a case study, we compare egoistic AVs to our altruistic autonomous agents in a highway merging case study and demonstrate a significant improvement in the number of successful merges as well as the overall traffic flow and safety.