APReL: A Library for Active Preference-based Reward Learning Algorithms

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.

Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic

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 drivers 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.

Cooperative Autonomous Vehicles that Sympathize with Human Drivers

Widespread adoption of autonomous vehicles will not become a reality until solutions are developed that enable these intelligent agents to co-exist with humans. This includes safely and efficiently interacting with human-driven vehicles, especially in both conflictive and competitive scenarios. We build up on the prior work on socially-aware navigation and borrow the concept of social value orientation from psychology -- that formalizes how much importance a person allocates to the welfare of others -- in order to induce altruistic behavior in autonomous driving. In contrast with existing works that explicitly model the behavior of human drivers and rely on their expected response to create opportunities for cooperation, our Sympathetic Cooperative Driving (SymCoDrive) paradigm trains altruistic agents that realize safe and smooth traffic flow in competitive driving scenarios only from experiential learning and without any explicit coordination. We demonstrate a significant improvement in both safety and traffic-level metrics as a result of this altruistic behavior and importantly conclude that the level of altruism in agents requires proper tuning as agents that are too altruistic also lead to sub-optimal traffic flow. The code and supplementary material are available at: https://symcodrive.toghi.net/

Social Coordination and Altruism in Autonomous Driving

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 AVs 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.

Exchangeable Input Representations for Reinforcement Learning

Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in an input space that is a factor of $m!$ smaller for inputs of $m$ objects. We also show that our method is able to represent inputs over variable numbers of objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using naive approaches.

Continual adaptation for efficient machine communication

To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners.

Object Exchangeability in Reinforcement Learning: Extended Abstract

Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. In this work, we present an attention-based method to project inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in a search space that is a factor of m! smaller for inputs of m objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using naive approaches.

Unsupervised Visuomotor Control through Distributional Planning Networks

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are not directly accessible. To enable robots to autonomously learn skills, we instead consider the problem of reinforcement learning without access to rewards. We aim to learn an unsupervised embedding space under which the robot can measure progress towards a goal for itself. Our approach explicitly optimizes for a metric space under which action sequences that reach a particular state are optimal when the goal is the final state reached. This enables learning effective and control-centric representations that lead to more autonomous reinforcement learning algorithms. Our experiments on three simulated environments and two real-world manipulation problems show that our method can learn effective goal metrics from unlabeled interaction, and use the learned goal metrics for autonomous reinforcement learning.