Search Results for author:
Found 13 papers, 7 papers with code
How Can LLM Guide RL? A Value-Based Approach
Specifically, we develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning, particularly when the difference between the ideal policy and the LLM-informed policy is small, which suggests that the initial policy is close to optimal, reducing the need for further exploration.
Identifying Reaction-Aware Driving Styles of Stochastic Model Predictive Controlled Vehicles by Inverse Reinforcement Learning
Nevertheless, an important indicator of the driving style, i. e., how an AV reacts to its nearby AVs, is not fully incorporated in the feature design of previous ME-IRL methods.
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions.
Cooperative Tuning of Multi-Agent Optimal Control Systems
Different from classical techniques for tuning parameters in a controller, we allow tunable parameters appearing in both the system dynamics and the objective functions of each agent.
Distributed Differentiable Dynamic Game for Multi-robot Coordination
In the inverse problem, where each robot aims to find (learn) its objective (and dynamics) parameters to mimic given coordination demonstrations, D3G proposes a differentiation solver based on Differential Pontryagin's Maximum Principle, which allows each robot to update its parameters in a distributed and coordinated manner.
Learning Linear Complementarity Systems
This paper investigates the learning, or system identification, of a class of piecewise-affine dynamical systems known as linear complementarity systems (LCSs).
Safe Pontryagin Differentiable Programming
We propose a Safe Pontryagin Differentiable Programming (Safe PDP) methodology, which establishes a theoretical and algorithmic framework to solve a broad class of safety-critical learning and control tasks -- problems that require the guarantee of safety constraint satisfaction at any stage of the learning and control progress.
Learning from Human Directional Corrections
This paper proposes a novel approach that enables a robot to learn an objective function incrementally from human directional corrections.
Learning Objective Functions Incrementally by Inverse Optimal Control
This paper proposes an inverse optimal control method which enables a robot to incrementally learn a control objective function from a collection of trajectory segments.
Robotics
Learning from Sparse Demonstrations
The time stamps of the keyframes can be different from the time of the robot's actual execution.
Neural Certificates for Safe Control Policies
This paper develops an approach to learn a policy of a dynamical system that is guaranteed to be both provably safe and goal-reaching.
Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework
This paper develops a Pontryagin Differentiable Programming (PDP) methodology, which establishes a unified framework to solve a broad class of learning and control tasks.
Inverse Optimal Control with Incomplete Observations
We handle the problem by proposing the recovery matrix, which establishes a relationship between available observations of the trajectory and weights of given candidate features.
Robotics Systems and Control
