Foundation reinforcement learning: towards embodied generalist agents with foundation prior assistance

W Ye, Y Zhang, M Wang, S Wang, X Gu, P Abbeel… - 2023 - openreview.net
Recently, people have shown that large-scale pre-training from diverse internet-scale data is
the key to building a generalist model, as witnessed in the natural language processing …

Reinforcement Learning with Foundation Priors: Let Embodied Agent Efficiently Learn on Its Own

W Ye, Y Zhang, H Weng, X Gu, S Wang… - … Conference on Robot …, 2024 - openreview.net
Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks.
However, it is challenging to apply the RL algorithms directly in the real world. For one thing …

Exploring Under Constraints with Model-Based Actor-Critic and Safety Filters

A Agha, B Kayalibay, A Mirchev… - … Conference on Robot …, 2024 - openreview.net
Applying reinforcement learning (RL) to learn effective policies on physical robots without
supervision remains challenging when it comes to tasks where safe exploration is critical …

Sample-efficient and occlusion-robust reinforcement learning for robotic manipulation via multimodal fusion dualization and representation normalization

S Noh, W Lee, H Myung - Neural Networks, 2025 - Elsevier
Recent advances in visual reinforcement learning (visual RL), which learns from high-
dimensional image observations, have narrowed the gap between state-based and image …

The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning

M Schneider, R Krug, N Vaskevicius, L Palmieri… - ar**
H Lin, B Li, CW Wong, J Rojas, X Chu… - arxiv preprint arxiv …, 2024 - arxiv.org
Intelligent vision control systems for surgical robots should adapt to unknown and diverse
objects while being robust to system disturbances. Previous methods did not meet these …

Model-Free versus Model-Based Reinforcement Learning for Fixed-Wing UAV Attitude Control Under Varying Wind Conditions

D Olivares, P Fournier, P Vasishta, J Marzat - arxiv preprint arxiv …, 2024 - arxiv.org
This paper evaluates and compares the performance of model-free and model-based
reinforcement learning for the attitude control of fixed-wing unmanned aerial vehicles using …

Bisimulation metric for Model Predictive Control

Y Shimizu, M Tomizuka - arxiv preprint arxiv:2410.04553, 2024 - arxiv.org
Model-based reinforcement learning has shown promise for improving sample efficiency
and decision-making in complex environments. However, existing methods face challenges …