Sample-efficient Reinforcement Learning in Robotic Table Tennis

Tebbe, Jonas; Krauch, Lukas; Gao, Yapeng; Zell, Andreas

doi:10.48550/arxiv.2011.03275

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, collecting a sufficient number of samples is not always feasible due to computational and/or quantity of interaction limitations. Recently, using model-based RL to improve sample efficiency is gaining more attraction [189], [190].…”

Section: A Sample Efficiencymentioning

confidence: 99%

Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

Majid

Saaybi

François-Lavet

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) and evolution strategies (ESs) have surpassed human-level control in many sequential decision-making problems, yet many open challenges still exist. To get insights into the strengths and weaknesses of DRL versus ESs, an analysis of their respective capabilities and limitations is provided. After presenting their fundamental concepts and algorithms, a comparison is provided on key aspects, such as scalability, exploration, adaptation to dynamic environments, and multiagent learning. Current research challenges are also discussed, including sample efficiency, exploration versus exploitation, dealing with sparse rewards, and learning to plan. Then, the benefits of hybrid algorithms that combine DRL and ESs are highlighted.

show abstract

Section: A Sample Efficiencymentioning

confidence: 99%

Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

Majid

Saaybi

François-Lavet

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Several research projects have been conducted on using reinforcement learning for performing controlled tasks and utilizing only visual information. As mentioned above, one of the major challenges in developing advanced robotic platforms is the limitations in obtaining quality data for RL [4]. Sim2Real is a term used in research for transferring skills learnt through a simulated virtual environment.…”

Section: Related Workmentioning

confidence: 99%

Bridging the Reality Gap Between Virtual and Physical Environments Through Reinforcement Learning

Ranaweera

Mahmoud

2023

IEEE Access

View full text Add to dashboard Cite

Creating Reinforcement learning(RL) agents that can perform tasks in the real-world robotic systems remains a challenging task due to inconsistencies between the virtual-and the real-world. This is known as the ''reality-gap'' which hinders the performance of a RL agent trained in a virtual environment. The research describes the techniques used to train the models, generate randomized environments, reward function, and techniques utilized to transfer the model to the physical environment for evaluation. For this investigation, a low-cost 3-degrees-of-freedom (DOF) Steward platform was 3D modeled and created virtually and physically. The goal of the 3D-Stewart platform was to guide and balance the marble towards the center. Custom end-to-end APIs were developed to interact with the Godot game engine, manipulate physics and dynamics, interact with the in-game lighting and perform environment randomizations. Two RL algorithms: Q-learning and Actor-Critic, were implemented to evaluate the performance by using domain randomization and induced noise to bridge the reality gap. For Q-learning, raw frames were used to make predictions while Actor-Critic utilized marble position, velocity vector and relative position by preprocessing captured frames. The experimental results show the effectiveness of domain randomization and introduction of noise during the training.

show abstract

“…One of the major problems in robot training is the difficulty of transferring the trained model to the real-world robot. This is often due to lack of quality training data, sample inefficiency and the cost of acquiring real-world data [4]. The main motivation of Sim2Real learning is to solve the domain gap due to insufficient training data by utilizing a virtual environment that allows to obtain necessary training data.…”

Section: Related Workmentioning

confidence: 99%

Bridging Reality Gap Between Virtual and Physical Robot through Domain Randomization and Induced Noise

Ranaweera¹,

Mahmoud²

2022

Proceedings of the Canadian Conference on Artificial Intelligence

View full text Add to dashboard Cite

This paper investigates techniques that can be utilized to bridge the reality gap between virtual and physical robots, by implementing a virtual environment and a physical robotic platform to evaluate the robustness of transfer learning from virtual to real-world robots. The proposed approach utilizes two reinforcement (RL) learning methods: deep Q-learning and Actor-Critic methodology to create a model that can learn from a virtual environment and performs in a physical environment. Techniques such as domain randomization and induced noise during training were utilized to bring variability and ultimately improve the learning policies. The experimental results demonstrate the effectiveness of the Actor-Critic reinforcement learning technique to bridge the reality gap.

show abstract

Sample-efficient Reinforcement Learning in Robotic Table Tennis

Cited by 4 publications

References 0 publications

Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

Bridging the Reality Gap Between Virtual and Physical Environments Through Reinforcement Learning

Bridging Reality Gap Between Virtual and Physical Robot through Domain Randomization and Induced Noise

Contact Info

Product

Resources

About