Skip to main content

2021 | OriginalPaper | Buchkapitel

Critic Guided Segmentation of Rewarding Objects in First-Person Views

verfasst von : Andrew Melnik, Augustin Harter, Christian Limberg, Krishan Rana, Niko Sünderhauf, Helge Ritter

Erschienen in: KI 2021: Advances in Artificial Intelligence

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic’s score of a high score image and increase the critic’s score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition. Video demonstration and code: https://​rebrand.​ly/​critic-guided-segmentation.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
2.
Zurück zum Zitat Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. In: International Conference on Machine Learning, pp. 1792–1801. PMLR (2018) Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. In: International Conference on Machine Learning, pp. 1792–1801. PMLR (2018)
3.
Zurück zum Zitat Gunning, D., Aha, D.: Darpa’s explainable artificial intelligence (XAI) program. AI Mag. 40(2), 44–58 (2019) Gunning, D., Aha, D.: Darpa’s explainable artificial intelligence (XAI) program. AI Mag. 40(2), 44–58 (2019)
5.
Zurück zum Zitat Harter, A., Melnik, A., Kumar, G., Agarwal, D., Garg, A., Ritter, H.: Solving physics puzzles by reasoning about paths. In: 1st NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning (2020). https://arxiv.org/abs/2011.07357 Harter, A., Melnik, A., Kumar, G., Agarwal, D., Garg, A., Ritter, H.: Solving physics puzzles by reasoning about paths. In: 1st NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning (2020). https://​arxiv.​org/​abs/​2011.​07357
9.
Zurück zum Zitat Konen, K., Korthals, T., Melnik, A., Schilling, M.: Biologically-inspired deep reinforcement learning of modular control for a six-legged robot. In: 2019 IEEE International Conference on Robotics and Automation Workshop on Learning Legged Locomotion Workshop, (ICRA) 2019, Montreal, CA, 20–25 May 2019 (2019) Konen, K., Korthals, T., Melnik, A., Schilling, M.: Biologically-inspired deep reinforcement learning of modular control for a six-legged robot. In: 2019 IEEE International Conference on Robotics and Automation Workshop on Learning Legged Locomotion Workshop, (ICRA) 2019, Montreal, CA, 20–25 May 2019 (2019)
10.
Zurück zum Zitat König, P., Melnik, A., Goeke, C., Gert, A.L., König, S.U., Kietzmann, T.C.: Embodied cognition. In: 2018 6th International Conference on Brain-Computer Interface (BCI), pp. 1–4. IEEE (2018) König, P., Melnik, A., Goeke, C., Gert, A.L., König, S.U., Kietzmann, T.C.: Embodied cognition. In: 2018 6th International Conference on Brain-Computer Interface (BCI), pp. 1–4. IEEE (2018)
13.
Zurück zum Zitat Melnik, A., Bramlage, L., Voss, H., Rossetto, F., Ritter, H.: Combining causal modelling and deep reinforcement learning for autonomous agents in minecraft. In: 4th Workshop on Semantic Policy and Action Representations for Autonomous Robots at IROS 2019 (2019) Melnik, A., Bramlage, L., Voss, H., Rossetto, F., Ritter, H.: Combining causal modelling and deep reinforcement learning for autonomous agents in minecraft. In: 4th Workshop on Semantic Policy and Action Representations for Autonomous Robots at IROS 2019 (2019)
14.
Zurück zum Zitat Melnik, A., Fleer, S., Schilling, M., Ritter, H.: Modularization of end-to-end learning: case study in arcade games. In: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Workshop on Causal Learning (2018). https://arxiv.org/pdf/1901.09895.pdf Melnik, A., Fleer, S., Schilling, M., Ritter, H.: Modularization of end-to-end learning: case study in arcade games. In: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Workshop on Causal Learning (2018). https://​arxiv.​org/​pdf/​1901.​09895.​pdf
17.
Zurück zum Zitat Olah, C., Mordvintsev, A., Schubert, L.: Feature visualization. Distill 2(11), e7 (2017)CrossRef Olah, C., Mordvintsev, A., Schubert, L.: Feature visualization. Distill 2(11), e7 (2017)CrossRef
18.
Zurück zum Zitat Olah, C., et al.: The building blocks of interpretability. Distill 3(3), e10 (2018)CrossRef Olah, C., et al.: The building blocks of interpretability. Distill 3(3), e10 (2018)CrossRef
20.
Zurück zum Zitat Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013) Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:​1312.​6034 (2013)
21.
Zurück zum Zitat Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps (2014) Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps (2014)
22.
Zurück zum Zitat Srinivas, A., Laskin, M., Abbeel, P.: Curl: contrastive unsupervised representations for reinforcement learning. arXiv preprint arXiv:2004.04136 (2020) Srinivas, A., Laskin, M., Abbeel, P.: Curl: contrastive unsupervised representations for reinforcement learning. arXiv preprint arXiv:​2004.​04136 (2020)
Metadaten
Titel
Critic Guided Segmentation of Rewarding Objects in First-Person Views
verfasst von
Andrew Melnik
Augustin Harter
Christian Limberg
Krishan Rana
Niko Sünderhauf
Helge Ritter
Copyright-Jahr
2021
DOI
https://doi.org/10.1007/978-3-030-87626-5_25