Abstract
Current research in Reinforcement Learning (RL) is based on closed-world learning environment where the environment remains fixed and unchanged throughout the agent’s training and application session. The fixed environment may be prone to failure when the agents incorporate under novel unseen situations. To overcome the drawback of the existing closed-world model, an Open-world learning model is required which can classify the novelty occurring in an environment in a hierarchical manner. The proposed control suite with open world novelty generator is an attempt to augment the machine learning environment for authoring the novelty in actors, interactions, and environment of standardized Reinforcement learning toolkits such as UnityML, OpenAI Gym, and DeepMind Control Suite in real-time. Such a tool will provide an opportunity to the RL researchers to simulate the Open-world learning model and test their algorithms within the standardized closed-world learning environments of the standardized RL toolkits.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Silver, D., Huang, A., Maddison, C., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484–489 (2016)
AlphaGo Homepage. https://deepmind.com/research/case-studies/alphago-the-story-so-far
Science of Artificial Intelligence and Learning for Open-world Novelty (SAIL-ON), HR001119S0038
Chen, Z., Liu, B.: Open-World Learning, 2nd edn. Morgan & Claypool Publishers. Lifelong Machine Learning (2018)
Fei, G., Wang, S., Liu, B.: Learning cumulatively to become more knowledgeable. In: KDD (2016)
Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)
Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)
Tassa, Y., et al.: DeepMind Control Suite. ArXiv e-prints (2018)
Koenig, N., Howard, A.: Design and use paradigms for gazebo, an open-source multi-robot simulator. In: Intelligent Robots and Systems, (IROS 2004) (2004)
Webots. Mobile Robot Simulation Software. http://www.cyberbotics.com.Open-source
Alkilabi, M.H.M., Narayan, A., Tuci, E.: Cooperative object transport with a swarm of e-puck robots: robustness and scalability of evolved collective strategies. Swarm Intell. 11(3–4), 185–209 (2017). https://doi.org/10.1007/s11721-017-0135-8
Gan, C., et al.: The ThreeDWorld transport challenge: a visually guided task-and-motion planning benchmark for physically realistic embodied AI. arXiv preprint arXiv:2103.14025 (2021)
Rizzardo, C., Katyara, S., Fernandes, M., Chen, F.: The importance and the limitations of Sim2Real for robotic manipulation in precision agriculture. In: 2nd Workshop on Closing the Reality Gap in Sim2Real Transfer for Robotics, RSS (2020)
Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura 2012, pp. 5026–5033 (2012)
Acknowledgments
This work was support by the Ministry of Science and ICT (MSIT), Korea, by (No. 2020–0-00056, to create AI systems that act appropriately and effectively in novel situations that occur in open worlds) supervised by IITP.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lee, S., Park, J., Suk, H., Kim, T., Yadav, P., Kim, S. (2021). An Open-World Novelty Generator for Authoring Reinforcement Learning Environment of Standardized Toolkits. In: Chomphuwiset, P., Kim, J., Pawara, P. (eds) Multi-disciplinary Trends in Artificial Intelligence. MIWAI 2021. Lecture Notes in Computer Science(), vol 12832. Springer, Cham. https://doi.org/10.1007/978-3-030-80253-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-80253-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80252-3
Online ISBN: 978-3-030-80253-0
eBook Packages: Computer ScienceComputer Science (R0)