Meta-learning control algorithm with finite-time guarantees for unknown systems.
problem Online control of unknown linear systems with constraints.
method Provable regret guarantees for an iterative control algorithm.
result Regret bounds of O(T3/4) for controller cost and constraint violation. Iterative method learns unknown constraints for MPC control.
problem Learning to satisfy unknown polyhedral state constraints in iterative MPC.
method Collects and improves estimates of unknown constraints using collected data, designs an MPC controller to satisfy the estimated constraints.
result Robust and probabilistic guarantees of constraint satisfaction as a function of task iterations.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
This work uses QPGPs to improve ILC performance in repetitive tasks.
problem Performance degradation in repetitive motion tasks due to environmental changes and robot wear.
method Incorporates Quasi-Periodic Gaussian Processes into a predictive ILC framework.
result The proposed approach achieves faster convergence and robustness under disturbances.
MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.
problem Optimizing risk in reinforcement learning control problems.
method Mean-Variance Policy Iteration (MVPI) framework for risk-averse control in MDPs.
result Risk-averse TD3 outperforms previous methods in robot simulation tasks.
Robust Q-learning for mean-field control under Wasserstein uncertainty
problem Mean-field control under Wasserstein uncertainty
method Quantization-and-projection scheme with Wasserstein dual reformulation
result Convergence and finite-time iteration bounds
Adaptive optimal control using value iteration initiated from a stabilizing control policy is theoretically analyzed in terms of stability of the system during the learning stage without ignoring the effects of approximation errors. This analysis includes the system operated using any single/constant resulting control …
Improving optimization for iterate-averaged language models
problem How to optimize the averaged model returned by Language Model pipelines
method Formulating optimizer design as an optimal-control problem
result Proven convergence rate and strict improvement in squared error
Develops a reinforcement learning algorithm for learning deterministic equilibrium policies in time-inconsistent control problems.
problem Learning equilibrium policies in time-inconsistent control problems.
method Continuous-time model-free reinforcement learning algorithm using deterministic policy gradient approach.
result Learned equilibrium policies in general time-inconsistent control problems.
PACE optimizes training for averaged language models, improving performance.
problem How to optimize training for averaged language model iterates.
method Formulated as an optimal-control problem, solved for minimizing error of the average with a penalty on intervention size.
result PACE improves the limiting squared error of the iterate-average estimator by an arbitrarily large factor on some instances.
This paper presents several numerical applications of deep learning-based algorithms that have been introduced in [HPBL18]. Numerical and comparative tests using TensorFlow illustrate the performance of our different algorithms, namely control learning by performance iteration (algorithms NNcontPI and ClassifPI), contr…
This paper addresses the model-free nonlinear optimal problem with generalized cost functional, and a data-based reinforcement learning technique is developed. It is known that the nonlinear optimal control problem relies on the solution of the Hamilton-Jacobi-Bellman (HJB) equation, which is a nonlinear partial differ…
Unified reinforcement learning methods using hybrid inference.
problem Combining model-based and model-free reinforcement learning approaches.
method Control as Hybrid Inference (CHI) framework.
result CHI algorithm balances model-based and model-free learning.
In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for continuous-time systems, policy iteration based QL (PIQL) and value iteration based…
This paper analyzes a simplified strategy for nonlinear control using local linear models and iLQR updates.
problem Nonlinear policy optimization in control systems.
method Iterative estimation of local linear models and iLQR-like policy updates.
result Demonstrates polynomial sample complexity and overcomes exponential problem horizon dependence.
Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step predictions in general leads to an analytically intractable problem. While approximation methods exist, they do not come with guarantees, mak…
Adaptive optimal control of nonlinear dynamic systems with deterministic and known dynamics under a known undiscounted infinite-horizon cost function is investigated. Policy iteration scheme initiated using a stabilizing initial control is analyzed in solving the problem. The convergence of the iterations and the optim…
The paper reclassifies RL algorithms using inference concepts.
problem To provide a unified perspective on RL algorithms.
method Using the control as inference framework, the paper classifies RL algorithms as amortised and iterative inference.
result A wide range of RL algorithms can be classified in this new manner.
New framework calibrates models to control risk under performativity.
problem Calibrating models to ensure reliable decision-making under performativity.
method Iteratively refined calibration process for different risk measures and tail bounds.
result Statistically rigorous risk control under performativity demonstrated.
Deep learning solves complex stochastic control with jumps.
problem Solving high-dimensional stochastic control tasks with jumps.
method Model-based approach using two neural networks, iteratively trained with objectives derived from the Hamilton-Jacobi-Bellman equation.
result Demonstrates effectiveness in solving complex high-dimensional stochastic control tasks.
We analyze stochastic approximation with Markov noise for reinforcement learning.
problem Asymptotic convergence analysis of stochastic approximation with controlled Markov noise.
method Relating to limiting differential inclusions and ergodic occupation measures.
result First informative error bounds on function approximation for policy evaluation.
New method controls sparse feature updates in deep networks.
problem Understanding sparse feature updates in deep networks during training.
method Iterative linearised training method to control sparse feature updates.
result Iterative linearised training surprisingly performs on par with standard training, requiring less frequent feature learning.
Optimizes control of noisy discrete systems without system matrix knowledge.
problem Optimal control of discrete-time systems with additive and multiplicative noises.
method Stochastic Lyapunov and Riccati equations, model-free reinforcement learning.
result Model-free reinforcement learning algorithm converges to optimal control policy.
Proposes DIAL-GNN for joint graph structure and embedding learning.
problem Joint learning of graph structure and embeddings.
method Adapted graph regularization, iterative method for graph structure learning.
result Consistently outperforms state-of-the-art baselines in downstream tasks and computational time.
Survey of theoretical foundations for policy optimization in control.
problem Understanding the theoretical properties of gradient-based methods in control and reinforcement learning.
method Interdisciplinary review of optimization landscape, convergence, and sample complexity for various control problems.
result Recent theoretical results on stability and robustness in learning-based control.
New approach uses hinge loss for iterative regularization in classification.
problem Improving classification accuracy through regularization.
method Develops an iterative regularization approach based on hinge loss.
result Proves convergence and rates of convergence for classification.
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using generic priors on the state characteristics. However, the diversity in appl…
We propose a novel reformulation of the stochastic optimal control problem as an approximate inference problem, demonstrating, that such a interpretation leads to new practical methods for the original problem. In particular we characterise a novel class of iterative solutions to the stochastic optimal control problem …
New algorithm achieves logarithmic regret for adversarial online control.
problem Online linear-quadratic control in systems with adversarial disturbances.
method Characterization of optimal offline control law, reduced to online learning with approximate advantage functions.
result First algorithm with logarithmic regret for arbitrary adversarial disturbance sequences.
We consider in this paper the regularity problem for time-optimal trajectories of a single-input control-affine system on a n-dimensional manifold. We prove that, under generic conditions on the drift and the controlled vector field, any control u associated with an optimal trajectory is smooth out of a countable set o…
New method controls mean exit time in stochastic systems using machine learning and quasipotential.
problem Controlling mean exit time in stochastic dynamical systems with white noise.
method Developed a neural network to compute the quasipotential function and designed an algorithm to calculate the controller.
result Effective and accurate control strategy demonstrated through numerical experiments.
Physics-informed learning framework for pH systems and EB-PBC control.
problem Control of port-Hamiltonian systems from trajectory data.
method Co-learning of pH system model and EB-PBC through alternating optimization.
result Proven stability and robustness of the learned controller.
New method learns diffusion bridges for rare events.
problem Simulating rare events in diffusion processes.
method Iterative online learning based on self-consistency.
result Strong performance in various empirical settings.
Algorithm optimizes system design and control for better rewards.
problem Optimizing system design and control for maximum rewards.
method Deep reinforcement learning combining policy gradient and model-based optimization.
result DEPS algorithm outperforms state-of-the-art methods in various environments.
The paper solves complex control problems using neural networks.
problem Solving McKean-Vlasov control problems.
method Mean-field neural networks and algorithms based on dynamic programming and stochastic maximum principle.
result Extensive numerical results show the accuracy of the proposed algorithms.
IDGL learns better graph structure and embeddings iteratively.
problem Improving graph neural network node embeddings and graph structure.
method Iterative Deep Graph Learning framework that dynamically stops when graph structure optimizes for downstream tasks.
result IDGL consistently outperforms state-of-the-art baselines on nine benchmarks.
Generalising the idea of the classical EM algorithm that is widely used for computing maximum likelihood estimates, we propose an EM-Control (EM-C) algorithm for solving multi-period finite time horizon stochastic control problems. The new algorithm sequentially updates the control policies in each time period using Mo…
Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to implement; however, they also come with fewer theoretical guarantees than model-bas…
A new ML algorithm solves complex economic control problems.
problem Solving high-dimensional, finite-horizon stochastic control problems in economics.
method Deep neural network representation of optimal policy functions with three key features.
result Efficiently solves various economic control problems including recursive utility and growth models.
New algorithms accelerate value function convergence in MDPs.
problem Accelerating convergence of value functions in Markov Decision Processes (MDPs).
method Operator Splitting Value Iteration (OS-VI) and OS-Dyna.
result Achieves much faster convergence rate with accurate models.
Paper tackles DOCTR-L with SciPhy RL, solving neural PDEs from data.
problem High-dimensional optimal control with stochastic policies.
method Soft HJB equation, Neural PDEs, Physics-Informed Neural Networks.
result Reduces DOCTR-L to solving neural PDEs from data.
Combines Lyapunov functions with controller synthesis for safe control policies.
problem Ensuring safety in controller design for nonlinear systems.
method Iterative algorithm combining Lyapunov function estimation and controller synthesis.
result Effective control policies with large safe regions are derived.
The paper proposes an iterative approach to batch reinforcement learning for safer and more informative data collection.
problem Learning policies that are too rigid and do not adapt to new data.
method Safe diversified model-based policy search in an iterative batch reinforcement learning framework.
result Improved learned policies through continuous data collection and adaptation.
A new approach to reinforcement learning improves policy performance by adjusting control frequency.
problem Improving reinforcement learning performance by optimizing control frequency.
method Introducing action persistence and a novel algorithm, PFQI, to learn optimal value function at a given persistence.
result PFQI effectively learns optimal value function with action persistence, improving reinforcement learning performance.
Bayesian optimization helps learn optimal controls for nuclear fusion reactions.
problem Learning optimal controls for nuclear fusion reactions to prolong plasma stability.
method Theoretical Bayesian optimization algorithm to recommend state-action pairs.
result More efficient use of simulator for learning optimal controls.
In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed con…
This study is aimed at answering the famous question of how the approximation errors at each iteration of Approximate Dynamic Programming (ADP) affect the quality of the final results considering the fact that errors at each iteration affect the next iteration. To this goal, convergence of Value Iteration scheme of ADP…
Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as ne…