Can Reinforcement Learning for Continuous Control Generalize Across Physics Engines?

2020-10-27 · Aaqib Parvez Mohammed, Matias Valdenegro-Toro

Reinforcement learning (RL) algorithms should learn as much as possible about the environment but not the properties of the physics engines that generate the environment. There are multiple algorithms that solve the task in a physics engine based environment but there is no work done so far to understand if the RL algorithms can generalize across physics engines. In this work, we compare the generalization performance of various deep reinforcement learning algorithms on a variety of control tasks. Our results show that MuJoCo is the best engine to transfer the learning to other engines. On the other hand, none of the algorithms generalize when trained on PyBullet. We also found out that various algorithms have a promising generalizability if the effect of random seeds can be minimized on their performance.

📄 PDF Abstract BibTeX arXiv:2010.14444

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-control Continuous ControlDeep Reinforcement LearningMuJoCoreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Maximum diffusion reinforcement learning

2023-09-26 · Thomas A. Berrueta, Allison Pinosky, Todd D. Murphey

Robots and animals both experience the world through their bodies and senses. Their embodiment constrains their experiences, ensuring they unfold continuously in space and time. As a result, the experiences of embodied a…

Decision Making reinforcement-learning Reinforcement Learning Self-Driving Cars

Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning

2025-09-08 · Vittorio Giammarino, Ruiqi Ni, Ahmed H. Qureshi arxiv

Offline Goal-Conditioned Reinforcement Learning (GCRL) holds great promise for domains such as autonomous navigation and locomotion, where collecting interactive data is costly and unsafe. However, it remains challenging…

Reinforcement Learning

I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement Learning

2024-05-14 · Yashuai Yan, Esteve Valls Mascaro, Tobias Egle, Dongheui Lee

Humanoid robots have the potential to mimic human motions with high visual fidelity, yet translating these motions into practical, physical execution remains a significant challenge. Existing techniques in the graphics c…

reinforcement-learning Reinforcement Learning

Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start

2025-11-07 · Fuyang Liu, Jiaqi Xu, Xiaowei Hu arxiv

Adverse weather severely impairs real-world visual perception, while existing vision models trained on synthetic data with fixed parameters struggle to generalize to complex degradations. To address this, we first constr…

Reinforcement Learning Image Restoration

Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics

2026-05-28 · Vittorio Giammarino, Anastasios Manganaris, Ahmed H. Qureshi arxiv

Learning to reach arbitrary goals from sparse feedback requires agents to infer a rich notion of reachability across state--goal pairs. Goal-conditioned reinforcement learning (GCRL) tackles this challenge by learning po…