Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass filters and smoothness rewards, are often employed to develop policies with smooth behaviors. However, because these techniques are non-differentiable and usually require tedious tuning of a large set of hyperparameters, they tend to require extensive manual tuning for each robotic platform. To address this challenge and establish a general technique for enforcing smooth behaviors, we propose a simple and effective method that imposes a Lipschitz constraint on a learned policy, which we refer to as Lipschitz-Constrained Policies (LCP). We show that the Lipschitz constraint can be implemented in the form of a gradient penalty, which provides a differentiable objective that can be easily incorporated with automatic differentiation frameworks. We demonstrate that LCP effectively replaces the need for smoothing rewards or low-pass filters and can be easily integrated into training frameworks for many distinct humanoid robots. We extensively evaluate LCP in both simulation and real-world humanoid robots, producing smooth and robust locomotion controllers. All simulation and deployment code, along with complete checkpoints, is available on our project page: https://lipschitz-constrained-policy.github.io.

Multi-Robot Task Allocation (MRTA) is a problem that arises in many application domains including package delivery, warehouse robotics, and healthcare. In this work, we consider the problem of MRTA for a dynamic stream of tasks with task deadlines and capacitated agents (capacity for more than one simultaneous task). Previous work commonly focuses on the static case, uses specialized algorithms for restrictive task specifications, or lacks guarantees. We propose an approach to Dynamic MRTA for capacitated robots that is based on Satisfiability Modulo Theories (SMT) solving and addresses these concerns. We show our approach is both sound and complete, and that the SMT encoding is general, enabling extension to a broader class of task specifications. We show how to leverage the incremental solving capabilities of SMT solvers, keeping learned information when allocating new tasks arriving online, and to solve non-incrementally, which we provide runtime comparisons of. Additionally, we provide an algorithm to start with a smaller but potentially incomplete encoding that can iteratively be adjusted to the complete encoding. We evaluate our method on a parameterized set of benchmarks encoding multi-robot delivery created from a graph abstraction of a hospital-like environment. The effectiveness of our approach is demonstrated using a range of encodings, including quantifier-free theories of uninterpreted functions and linear or bitvector arithmetic across multiple solvers.

Robotic interaction in fast-paced environments presents a substantial challenge, particularly in tasks requiring the prediction of dynamic, non-stationary objects for timely and accurate responses. An example of such a task is ping-pong, where the physical limitations of a robot may prevent it from reaching its goal in the time it takes the ball to cross the table. The scene of a ping-pong match contains rich visual information of a player's movement that can allow future game state prediction, with varying degrees of uncertainty. To this aim, we present a visual modeling, prediction, and control system to inform a ping-pong playing robot utilizing visual model uncertainty to allow earlier motion of the robot throughout the game. We present demonstrations and metrics in simulation to show the benefit of incorporating model uncertainty, the limitations of current standard model uncertainty estimators, and the need for more verifiable model uncertainty estimation. Our code is publicly available.

Abstract-- In this work we present a multi-armed bandit framework for online expert selection in Markov decision processes and demonstrate its use in high-dimensional settings. Our method takes a set of candidate expert policies and switches between them to rapidly identify the best performing expert using a variant of the classical upper confidence bound algorithm, thus ensuring low regret in the overall performance of the system. This is useful in applications where several expert policies may be available, and one needs to be selected at runtime for the underlying environment. Markov decision processes (MDPs) represent a mathematical reach a set of high-reward states. For the high-dimensional framework for dealing with decision problems in case, we will use the Seaquest video game environment, many fields. It is usually hard, however, to predict how shown in Figure 1, where each expert policy is trained under changes in the underlying MDP might affect the performance different observation models.

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such behavior is more succinctly described by a simple reward combined with a set of hard constraints. In this setting, the agent is attempting to maximize cumulative rewards subject to these given constraints on their behavior. We reformulate the problem of IRL on Markov Decision Processes (MDPs) such that, given a nominal model of the environment and a nominal reward function, we seek to estimate state, action, and feature constraints in the environment that motivate an agent's behavior. Our approach is based on the Maximum Entropy IRL framework, which allows us to reason about the likelihood of an expert agent's demonstrations given our knowledge of an MDP. Using our method, we can infer which constraints can be added to the MDP to most increase the likelihood of observing these demonstrations. We present an algorithm which iteratively infers the Maximum Likelihood Constraint to best explain observed behavior, and we evaluate its efficacy using both simulated behavior and recorded data of humans navigating around an obstacle.

We show by counterexample that policy-gradient algorithms have no guarantees of even local convergence to Nash equilibria in continuous action and state space multi-agent settings. To do so, we analyze gradient-play in $N$-player general-sum linear quadratic games. In such games the state and action spaces are continuous and the unique global Nash equilibrium can be found be solving coupled Ricatti equations. Further, gradient-play in LQ games is equivalent to multi-agent policy gradient. We first prove that the only critical point of the gradient dynamics in these games is the unique global Nash equilibrium. We then give sufficient conditions under which policy gradient will avoid the Nash equilibrium, and generate a large number of general-sum linear quadratic games that satisfy these conditions. The existence of such games indicates that one of the most popular approaches to solving reinforcement learning problems in the classic reinforcement learning setting has no guarantee of convergence in multi-agent settings. Further, the ease with which we can generate these counterexamples suggests that such situations are not mere edge cases and are in fact quite common.

In recent years, data has played an increasingly important role in the economy as a good in its own right. In many settings, data aggregators cannot directly verify the quality of the data they purchase, nor the effort exerted by data sources when creating the data. Recent work has explored mechanisms to ensure that the data sources share high quality data with a single data aggregator, addressing the issue of moral hazard. Oftentimes, there is a unique, socially efficient solution. In this paper, we consider data markets where there is more than one data aggregator. Since data can be cheaply reproduced and transmitted once created, data sources may share the same data with more than one aggregator, leading to free-riding between data aggregators. This coupling can lead to non-uniqueness of equilibria and social inefficiency. We examine a particular class of mechanisms that have received study recently in the literature, and we characterize all the generalized Nash equilibria of the resulting data market. We show that, in contrast to the single-aggregator case, there is either infinitely many generalized Nash equilibria or none. We also provide necessary and sufficient conditions for all equilibria to be socially inefficient. In our analysis, we identify the components of these mechanisms which give rise to these undesirable outcomes, showing the need for research into mechanisms for competitive settings with multiple data purchasers and sellers.

State-of-the-art neural networks are vulnerable to adversarial examples; they can easily misclassify inputs that are imperceptibly different than their training and test data. In this work, we establish that the use of cross-entropy loss function and the low-rank features of the training data have responsibility for the existence of these inputs. Based on this observation, we suggest that addressing adversarial examples requires rethinking the use of cross-entropy loss function and looking for an alternative that is more suited for minimization with low-rank features. In this direction, we present a training scheme called differential training, which uses a loss function defined on the differences between the features of points from opposite classes. We show that differential training can ensure a large margin between the decision boundary of the neural network and the points in the training dataset. This larger margin increases the amount of perturbation needed to flip the prediction of the classifier and makes it harder to find an adversarial example with small perturbations. We test differential training on a binary classification task with CIFAR-10 dataset and demonstrate that it radically reduces the ratio of images for which an adversarial example could be found -- not only in the training dataset, but in the test dataset as well.

We propose local symplectic surgery, a two-timescale procedure for finding local Nash equilibria in two-player zero-sum games. We first show that previous gradient-based algorithms cannot guarantee convergence to local Nash equilibria due to the existence of non-Nash stationary points. By taking advantage of the differential structure of the game, we construct an algorithm for which the local Nash equilibria are the only attracting fixed points. We also show that the algorithm exhibits no oscillatory behaviors in neighborhoods of equilibria and show that it has the same per-iteration complexity as other recently proposed algorithms. We conclude by validating the algorithm on two numerical examples: a toy example with multiple Nash equilibria and a non-Nash equilibrium, and the training of a small generative adversarial network (GAN).

Training a neural network with the gradient descent algorithm gives rise to a discrete-time nonlinear dynamical system. Consequently, behaviors that are typically observed in these systems emerge during training, such as convergence to an orbit but not to a fixed point or dependence of convergence on the initialization. Step size of the algorithm plays a critical role in these behaviors: it determines the subset of the local optima that the algorithm can converge to, and it specifies the magnitude of the oscillations if the algorithm converges to an orbit. To elucidate the effects of the step size on training of neural networks, we study the gradient descent algorithm as a discrete-time dynamical system, and by analyzing the Lyapunov stability of different solutions, we show the relationship between the step size of the algorithm and the solutions that can be obtained with this algorithm. The results provide an explanation for several phenomena observed in practice, including the deterioration in the training error with increased depth, the hardness of estimating linear mappings with large singular values, and the distinct performance of deep residual networks.