Search Results for author:
Found 13 papers, 4 papers with code
On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR
Designing a competent meta-reinforcement learning (meta-RL) algorithm in terms of data usage remains a central challenge to be tackled for its successful real-world applications.
Distributionally Robust Differential Dynamic Programming with Wasserstein Distance
To achieve this, we use the Kantrovich duality principle to decompose the value function in a novel way and derive closed-form expressions of the distributionally robust control and worst-case distribution policies to be used in each iteration of our DDP algorithm.
Wasserstein Distributionally Robust Control of Partially Observable Linear Stochastic Systems
Distributionally robust control (DRC) aims to effectively manage distributional ambiguity in stochastic systems.
Anderson Acceleration for Partially Observable Markov Decision Processes: A Maximum Entropy Approach
Inspired by the quasi-Newton interpretation of AA, we propose a maximum entropy variant of QMDP, which we call soft QMDP, to fully benefit from AA.
Wasserstein Distributionally Robust Control of Partially Observable Linear Systems: Tractable Approximation and Performance Guarantee
The key idea is to reformulate the WDRC problem as a novel minimax control problem with an approximate Wasserstein penalty.
On Affine Policies for Wasserstein Distributionally Robust Unit Commitment
The proposed model is formulated as a WDRO problem relying on an affine policy, which nests an infinite-dimensional worst-case expectation problem and satisfies the non-anticipativity constraint.
Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs
For linear bandits, we achieve $\tilde O(\min\{d\sqrt{K}, d^{1. 5}\sqrt{\sum_{k=1}^K \sigma_k^2}\} + d^2)$ where $d$ is the dimension of the features, $K$ is the time horizon, and $\sigma_k^2$ is the noise variance at time step $k$, and $\tilde O$ ignores polylogarithmic dependence, which is a factor of $d^3$ improvement.
Training Wasserstein GANs without gradient penalties
We propose a stable method to train Wasserstein generative adversarial networks.
On Anderson acceleration for partially observable Markov decision processes
This paper proposes an accelerated method for approximately solving partially observable Markov decision process (POMDP) problems offline.
Risk-sensitive safety analysis using Conditional Value-at-Risk
In addition, we propose a second definition for risk-sensitive safe sets and provide a tractable method for their estimation without using a parameter-dependent upper bound.
Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
In this paper, we propose Q-learning algorithms for continuous-time deterministic optimal control problems with Lipschitz continuous controls.
Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach
Our approach constructs a Lyapunov function with respect to a safe policy to restrain each policy improvement stage.
Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time
The performance of the proposed Q-learning algorithm is demonstrated using 1-, 10- and 20-dimensional dynamical systems.
