Related papers: Learning from Less: SINDy Surrogates in RL

This work proposes an iterative sparse-regularized regression method to recover governing equations of nonlinear dynamical systems from noisy state measurements. The method is inspired by the Sparse Identification of Nonlinear Dynamics…

We present Learning to Drive (L2D), a low-cost benchmark for real-world reinforcement learning (RL). L2D involves a simple and reproducible experimental setup where an RL agent has to learn to drive a Donkey car around three miniature…

Recently, large language models (LLMs) have shown strong potential in facilitating human-robotic interaction and collaboration. However, existing LLM-based systems often overlook the misalignment between human and robot perceptions, which…

The SINDy algorithm has been successfully used to identify the governing equations of dynamical systems from time series data. However, SINDy assumes the user has prior knowledge of the variables in the system and of a function library that…

This paper explores the combination of two intrinsic motivation strategies to improve the efficiency of reinforcement learning (RL) agents in environments with extreme sparse rewards, where traditional learning struggles due to infrequent…

Recent advances in reinforcement learning (RL) have increased the promise of introducing cognitive assistance and automation to robot-assisted laparoscopic surgery (RALS). However, progress in algorithms and methods depends on the…

Reinforcement learning (RL) in sparse-reward environments remains a significant challenge due to the lack of informative feedback. We propose a simple yet effective method that uses a small number of successful demonstrations to initialize…

This paper presents ``randomized SINDy", a sequential machine learning algorithm designed for dynamic data that has a time-dependent structure. It employs a probabilistic approach, with its PAC learning property rigorously proven through…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Sparse Identification of Nonlinear Dynamical Systems (SINDy) is a powerful tool for the data-driven discovery of governing equations. However, it encounters challenges when modeling complex dynamical systems involving high-order derivatives…

Sample efficiency in the face of computationally expensive simulations is a common concern in surrogate modeling. Current strategies to minimize the number of samples needed are not as effective in simulated environments with wide state…

Bridging the gap between data-rich training regimes and observation-sparse deployment conditions remains a central challenge in spatiotemporal field reconstruction, particularly when target domains exhibit distributional shifts,…

We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to the agent. The agent needs to quickly adapt to the task over…

Identifying governing equations in physical and biological systems from datasets remains a long-standing challenge across various scientific disciplines, providing mechanistic insights into complex system evolution. Common methods like…

We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to…

Neuromorphic computing systems are set to revolutionize energy-constrained robotics by achieving orders-of-magnitude efficiency gains, while enabling native temporal processing. Spiking Neural Networks (SNNs) represent a promising…

Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the…

Natural agents can effectively learn from multiple data sources that differ in size, quality, and types of measurements. We study this heterogeneity in the context of offline reinforcement learning (RL) by introducing a new, practically…

This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown…

Two current methods used to train autonomous cars are reinforcement learning and imitation learning. This research develops a new learning methodology and systematic approach in both a simulated and a smaller real world environment by…