Search Results for author:
Found 40 papers, 8 papers with code
Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
We show that whenever the topologies of $L^2$ and $\Psi_p$ are comparable on our hypothesis class $\mathscr{F}$ -- that is, $\mathscr{F}$ is a weakly sub-Gaussian class: $\|f\|_{\Psi_p} \lesssim \|f\|_{L^2}^\eta$ for some $\eta\in (0, 1]$ -- the empirical risk minimizer achieves a rate that only depends on the complexity of the class and second order statistics in its leading term.
Revisiting Energy Based Models as Policies: Ranking Noise Contrastive Estimation and Interpolating Energy Models
In this work, we revisit the choice of energy-based models (EBM) as a policy class.
Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
Large language models (LLMs) exhibit a wide range of promising capabilities -- from step-by-step planning to commonsense reasoning -- that may provide utility for robots, but remain prone to confidently hallucinated predictions.
Bootstrapped Representations in Reinforcement Learning
In this paper, we address this gap and provide a theoretical characterization of the state representation learnt by temporal difference learning (Sutton, 1988).
Safely Learning Dynamical Systems
For $T=2$, we give a semidefinite representation of the set of safe initial conditions and show that $\lceil n/2 \rceil$ trajectories generically suffice for safe learning.
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization
A common pipeline in learning-based control is to iteratively estimate a model of system dynamics, and apply a trajectory optimization algorithm - e. g.~$\mathtt{iLQR}$ - on the learned model to minimize a target cost.
Multi-Task Imitation Learning for Linear Dynamical Systems
In particular, we consider a setting where learning is split into two phases: (a) a pre-training step where a shared $k$-dimensional representation is learned from $H$ source policies, and (b) a target policy fine-tuning step where the learned representation is used to parameterize the policy class.
Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning
We find that by adjusting the data collection process we improve the quality of both the learned value functions and policies over a variety of baseline methods for data collection.
Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation
Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e. g., in cluttered home environments or in human-occupied public spaces.
Learning with little mixing
We study square loss in a realizable time-series framework with martingale difference noise.
TaSIL: Taylor Series Imitation Learning
We propose Taylor Series Imitation Learning (TaSIL), a simple augmentation to standard behavior cloning losses in the context of continuous control.
Learning from many trajectories
Specifically, we establish that the worst-case error rate of this problem is $\Theta(n / m T)$ whenever $m \gtrsim n$.
On the Generalization of Representations in Reinforcement Learning
We complement our theoretical results with an empirical survey of classic representation learning methods from the literature and results on the Arcade Learning Environment, and find that the generalization behaviour of learned representations is well-explained by their effective dimension.
Adversarially Robust Stability Certificates can be Sample-Efficient
Motivated by bridging the simulation to reality gap in the context of safety-critical systems, we consider learning adversarially robust stability certificates for unknown nonlinear dynamical systems.
Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations
Along with the optimization problem, we provide verifiable conditions in terms of the density of the data, smoothness of the system model and state estimator, and the size of the error bounds that guarantee validity of the obtained ROCBF.
Nonparametric adaptive control and prediction: theory and randomized algorithms
A key assumption in the theory of nonlinear adaptive control is that the uncertainty of the system can be expressed in the linear span of a set of known basis functions.
On the Sample Complexity of Stability Constrained Imitation Learning
We study the following question in the context of imitation learning for continuous control: how are the underlying stability properties of an expert policy reflected in the sample-complexity of an imitation learning task?
Learning Robust Hybrid Control Barrier Functions for Uncertain Systems
We identify sufficient conditions on the data such that feasibility of the optimization problem ensures correctness of the learned robust hybrid control barrier functions.
Regret Bounds for Adaptive Nonlinear Control
We study the problem of adaptively controlling a known discrete-time nonlinear system subject to unmodeled disturbances.
Safely Learning Dynamical Systems from Short Trajectories
For our first two results, we consider the setting of safely learning linear dynamics.
Learning Hybrid Control Barrier Functions from Data
Motivated by the lack of systematic tools to obtain safe control laws for hybrid systems, we propose an optimization-based framework for learning certifiably safe control laws from data.
Learning Stability Certificates from Data
Many existing tools in nonlinear control theory for establishing stability or safety of a dynamical system can be distilled to the construction of a certificate function that guarantees a desired property.
The role of optimization geometry in single neuron learning
Recent numerical experiments have demonstrated that the choice of optimization geometry used during training can impact generalization performance when learning expressive nonlinear model classes such as deep neural networks.
Learning Control Barrier Functions from Expert Demonstrations
Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process.
Observational Overfitting in Reinforcement Learning
A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process (MDP).
A Tutorial on Concentration Bounds for System Identification
We provide a brief tutorial on the use of concentration inequalities as they apply to system identification of state-space parameters of linear time invariant systems, with a focus on the fully observed setting.
From self-tuning regulators to reinforcement learning and back again
Machine and reinforcement learning (RL) are increasingly being applied to plan and control the behavior of autonomous systems interacting with the physical world.
Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator
We study the sample complexity of approximate policy iteration (PI) for the Linear Quadratic Regulator (LQR), building on a recent line of work using LQR as a testbed to understand the limits of reinforcement learning (RL) algorithms on continuous control tasks.
Certainty Equivalence is Efficient for Linear Quadratic Control
We show that for both the fully and partially observed settings, the sub-optimality gap between the cost incurred by playing the certainty equivalent controller on the true system and the cost incurred by using the optimal LQ controller enjoys a fast statistical rate, scaling as the square of the parameter error.
The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint
The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL).
Minimax Lower Bounds for $\mathcal{H}_\infty$-Norm Estimation
The problem of estimating the $\mathcal{H}_\infty$-norm of an LTI system from noisy input/output measurements has attracted recent attention as an alternative to parameter identification for bounding unmodeled dynamics in robust control.
Safely Learning to Control the Constrained Linear Quadratic Regulator
We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques.
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs.
Learning Contracting Vector Fields For Stable Imitation Learning
We propose a new non-parametric framework for learning incrementally stable dynamical systems x' = f(x) from a set of sampled trajectories.
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
We prove that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajectory.
Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator
Reinforcement learning (RL) has been successfully used to solve many continuous control tasks.
On the Sample Complexity of the Linear Quadratic Regulator
This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown.
Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification
We derive bounds on the number of noisy input/output samples from a stable linear time-invariant system that are sufficient to guarantee that the corresponding finite impulse response approximation is close to the true system in the $\mathcal{H}_\infty$-norm.
CYCLADES: Conflict-free Asynchronous Machine Learning
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting.
Large Scale Kernel Learning using Block Coordinate Descent
We demonstrate that distributed block coordinate descent can quickly solve kernel regression and classification problems with millions of data points.
