Learning Robust Controllers Via Probabilistic Model-Based Policy Search

2021-10-26 · Valentin Charvet, Bjørn Sand Jensen, Roderick Murray-Smith

Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from better sample efficiency than their model-free counterparts. We investigate whether controllers learned in such a way are robust and able to generalize under small perturbations of the environment. Our work is inspired by the PILCO algorithm, a method for probabilistic policy search. We show that enforcing a lower bound to the likelihood noise in the Gaussian Process dynamics model regularizes the policy updates and yields more robust controllers. We demonstrate the empirical benefits of our method in a simulation benchmark.

📄 PDF Abstract BibTeX arXiv:2110.13576

Code (0)

등록된 구현이 없습니다.

Tasks

Model-based Reinforcement Learningreinforcement-learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Generating Probabilistic Safety Guarantees for Neural Network Controllers

2021-03-01 · Sydney M. Katz, Kyle D. Julian, Christopher A. Strong, Mykel J. Kochenderfer

Neural networks serve as effective controllers in a variety of complex settings due to their ability to represent expressive policies. The complex nature of neural networks, however, makes their output difficult to verif…

Collision Avoidance

Are Agents Probabilistic Automata? A Trace-Based, Memory-Constrained Theory of Agentic AI

2025-10-27 · Roham Koohestani, Ziyou Li, Anton Podkopaev, Maliheh Izadi arxiv

This paper studies standard controller architectures for agentic AI and derives automata-theoretic models of their interaction behavior via trace semantics and abstraction. We model an agent implementation as a finite co…

Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers

2017-03-08 · Andreas Doerr, Duy Nguyen-Tuong, Alonso Marco, Stefan Schaal 외

PID control architectures are widely used in industrial applications. Despite their low number of open parameters, tuning multiple, coupled PID controllers can become tedious in practice. In this paper, we extend PILCO, …

A Model-Based Reinforcement Learning Approach for PID Design

2022-06-07 · Hozefa Jesawada, Amol Yerudkar, Carmen Del Vecchio, Navdeep Singh

Proportional-integral-derivative (PID) controller is widely used across various industrial process control applications because of its straightforward implementation. However, it can be challenging to fine-tune the PID p…

Model-based Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling

2019-10-23 · Heung-Chang Lee, Do-Guk Kim, Bohyung Han

We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models from the multinomial distribution on the po…

Neural Architecture Search reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)