相关论文: Algorithms for Deciding the Safety of States in Fu…

Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting in largely…

In this paper, we investigate a worst-case-scenario control problem with a partially observed state. We consider a non-stochastic formulation, where noises and disturbances in our dynamics are uncertain variables which take values in finite…

The standard version of the policy iteration (PI) algorithm fails for semicontinuous models, that is, for models with lower semicontinuous one-step costs and weakly continuous transition law. This is due to the lack of continuity properties…

It remains challenging to deploy existing risk-averse approaches to real-world applications. The reasons are multi-fold, including the lack of global optimality guarantee and the necessity of learning from long-term consecutive…

The decision and planning system for autonomous driving in urban environments is hard to design. Most current methods manually design the driving policy, which can be expensive to develop and maintain at scale. Instead, with imitation…

In recent years, stabilizing unknown dynamical systems has became a critical problem in control systems engineering. Addressing this for linear time-invariant (LTI) systems is an essential fist step towards solving similar problems for more…

Robust reinforcement learning (RL) aims to find a policy that optimizes the worst-case performance in the face of uncertainties. In this paper, we focus on action robust RL with the probabilistic policy execution uncertainty, in which,…

We consider the problem of designing a sequential decision making agent to maximize an unknown time-varying function which switches with time. At each step, the agent receives an observation of the function's value at a point decided by the…

Motivated by practical needs of experimentation and policy learning in online platforms, we study the problem of safe data collection. Specifically, our goal is to develop a logging policy that efficiently explores different actions to…

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard…

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or…

One of the main issues in Imitation Learning is the erroneous behavior of an agent when facing out-of-distribution situations, not covered by the set of demonstrations given by the expert. In this work, we tackle this problem by introducing…

Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and…

The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems. Since macro-actions last for stochastic…

In many reinforcement learning (RL) applications, we want policies that reach desired states and then keep the controlled system within an acceptable region around the desired states over an indefinite period of time. This latter objective…

Observational determinism is a security property that characterizes secure information flow for multithreaded programs. Most of the methods that have been used to verify observational determinism are based on either type systems or…

To design effective digital interventions, experimenters face the challenge of learning decision policies that balance multiple objectives using offline data. Often, they aim to develop policies that maximize goal outcomes, while ensuring…

We consider the problem of estimating the state of a noisy linear dynamical system when an unknown subset of sensors is arbitrarily corrupted by an adversary. We propose a secure state estimation algorithm, and derive (optimal) bounds on…

The ability to learn and execute optimal control policies safely is critical to realization of complex autonomy, especially where task restarts are not available and/or the systems are safety-critical. Safety requirements are often…

Reinforcement learning has been established over the past decade as an effective tool to find optimal control policies for dynamical systems, with recent focus on approaches that guarantee safety during the learning and/or execution phases.…