English
Related papers

Related papers: Algorithms for Deciding the Safety of States in Fu…

200 papers

We consider approximate dynamic programming in $\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy…

Machine Learning · Computer Science 2022-10-31 Gellért Weisz , András György , Tadashi Kozuno , Csaba Szepesvári

Given a policy of a Markov Decision Process, we define a SafeZone as a subset of states, such that most of the policy's trajectories are confined to this subset. The quality of a SafeZone is parameterized by the number of states and the…

Machine Learning · Computer Science 2023-10-10 Lee Cohen , Yishay Mansour , Michal Moshkovitz

Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement…

Systems and Control · Electrical Eng. & Systems 2025-03-20 Dongdong Li , Jiuxiang Dong

This paper presents a safe robust policy iteration (SR-PI) algorithm to design controllers with satisficing (good enough) performance and safety guarantee. This is in contrast to standard PI-based control design methods with no safety…

Systems and Control · Electrical Eng. & Systems 2020-09-16 Yuzhen Han , Hamidreza Modares

We present a data-driven optimal control framework that can be viewed as a generalization of the path integral (PI) control approach. We find iterative feedback control laws without parameterization based on probabilistic representation of…

Systems and Control · Computer Science 2016-02-02 Yunpeng Pan , Evangelos A. Theodorou , Michail Kontitsis

In this work we seek for an approach to integrate safety in the learning process that relies on a partly known state-space model of the system and regards the unknown dynamics as an additive bounded disturbance. We introduce a framework for…

Machine Learning · Computer Science 2018-11-12 Stanislav Fedorov , Antonio Candelieri

In this paper we propose an on-line policy iteration (PI) algorithm for finite-state infinite horizon discounted dynamic programming, whereby the policy improvement operation is done on-line, only for the states that are encountered during…

Optimization and Control · Mathematics 2021-06-03 Dimitri Bertsekas

Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy. We formalize the idea of safe learning in a…

Robotics · Computer Science 2017-05-17 David Held , Zoe McCarthy , Michael Zhang , Fred Shentu , Pieter Abbeel

In this paper, we propose a new policy iteration algorithm to compute the value function and the optimal controls of continuous time stochastic control problems. The algorithm relies on successive approximations using linear-quadratic…

Optimization and Control · Mathematics 2024-09-09 Dylan Possamaï , Ludovic Tangpi

We study safe policy improvement (SPI) for partially observable Markov decision processes (POMDPs). SPI is an offline reinforcement learning (RL) problem that assumes access to (1) historical data about an environment, and (2) the so-called…

Artificial Intelligence · Computer Science 2023-01-13 Thiago D. Simão , Marnix Suilen , Nils Jansen

We present an anytime algorithm which computes policies for decision problems represented as multi-stage influence diagrams. Our algorithm constructs policies incrementally, starting from a policy which makes no use of the available…

Artificial Intelligence · Computer Science 2013-02-01 Michael C. Horsch , David L. Poole

Solving Markov Decision Processes (MDPs) is a recurrent task in engineering. Even though it is known that solutions for minimizing the infinite horizon expected reward can be found in polynomial time using Linear Programming techniques,…

Computational Complexity · Computer Science 2014-10-29 Romain Hollanders , Balázs Gerencsér , Jean-Charles Delvenne , Raphaël M. Jungers

This paper considers optimal control of dynamical systems which are represented by nonlinear stochastic differential equations. It is well-known that the optimal control policy for this problem can be obtained as a function of a value…

Robotics · Computer Science 2014-05-30 Oktay Arslan , Evangelos Theodorou , Panagiotis Tsiotras

We consider the problem of learning a non-deterministic probabilistic system consistent with a given finite set of positive and negative tree samples. Consistency is defined with respect to strong simulation conformance. We propose learning…

Logic in Computer Science · Computer Science 2012-07-24 Anvesh Komuravelli , Corina S. Pasareanu , Edmund M. Clarke

Linear dynamical systems that obey stochastic differential equations are canonical models. While optimal control of known systems has a rich literature, the problem is technically hard under model uncertainty and there are hardly any…

Systems and Control · Electrical Eng. & Systems 2023-06-09 Mohamad Kazem Shirani Faradonbeh , Mohamad Sadegh Shirani Faradonbeh

We propose a safe exploration algorithm for deterministic Markov Decision Processes with unknown transition models. Our algorithm guarantees safety by leveraging Lipschitz-continuity to ensure that no unsafe states are visited during…

Robotics · Computer Science 2020-06-05 Erdem Bıyık , Jonathan Margoliash , Shahrouz Ryan Alimo , Dorsa Sadigh

The safe operation of an autonomous system is a complex endeavor, one pivotal element being its decision-making. Decision-making logic can formally be analyzed using model checking or other formal verification approaches. Yet, the…

Multiagent Systems · Computer Science 2023-10-05 Jan Vermaelen , Tom Holvoet

Considering uncertainties and disturbances is an important, yet challenging, step in successful decision making. The problem becomes more challenging in safety-constrained environments. In this paper, we propose a robust and safe trajectory…

Systems and Control · Electrical Eng. & Systems 2022-03-29 Hassan Almubarak , Evangelos A. Theodorou , Nader Sadegh

The question of knowing whether the policy Iteration algorithm (PI) for solving Markov Decision Processes (MDPs) has exponential or (strongly) polynomial complexity has attracted much attention in the last 50 years. Recently, Fearnley…

Computer Science and Game Theory · Computer Science 2011-08-19 Romain Hollanders , Jean-Charles Delvenne , Raphaël Jungers

We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to capture the system dynamics, based on the PILCO framework. Our…

Machine Learning · Statistics 2019-12-03 Kyriakos Polymenakos , Alessandro Abate , Stephen Roberts