Skip to content

Deep reinforcement learning applied to a novel 2d environment.

Notifications You must be signed in to change notification settings

bnestor/second-hand-rl

Repository files navigation

Deep RL for different physics

project forked from https://github.com/germain-hug/Deep-RL-Keras What didn't work for my environment was fixed with https://github.com/simoninithomas/Deep_reinforcement_learning_Course/tree/master/A2C%20with%20Sonic%20the%20Hedgehog

Running

$ python actor_critic.py

Results

alt text

References (Papers & Inspiration)

[1] W. Abdulla. Mask r-cnn for object detection and instance segmentation on keras and tensorflow. https://github.com/matterport/Mask RCNN, 2017. [2] R. Alp G ̈ uler, N. Neverova, and I. Kokkinos. DensePose: Dense Human Pose Estimation In The Wild. ArXiv e-prints , Feb. 2018. [3] M. Andrychowicz, F. Wolski, A. Ray, J. Schneider, R. Fong, P. Welinder, B. McGrew, J. Tobin, P. Abbeel, and W. Zaremba. Hindsight Experience Replay. arXiv e-prints , page arXiv:1707.01495, July 2017. [4] S. Bambach, S. Lee, D. J. Crandall, and C. Yu. Lending a hand: Detecting hands and recognizing activities in complex egocentric interactions. In The IEEE International Conference on Computer Vision (ICCV) , December 2015. [5] H. Caselles-Dupr ́e, L. Annabi, O. Hagen, M. Garcia-Ortiz, and D. Filliat. Flatland: a lightweight first-person 2-d environment for reinforcement learning. arXiv preprint arXiv:1809.00510 , 2018. [6] C. Chan, S. Ginosar, T. Zhou, and A. A. Efros. Everybody Dance Now. ArXiv e-prints , Aug. 2018. [7] K. He, G. Gkioxari, P. Doll ́ar, and R. Girshick. Mask R-CNN. ArXiv e-prints , Mar. 2017. [8] S. K. Kim, E. A. Kirchner, A. Stefes, and F. Kirchner. Intrinsic interactive reinforcement learning–using error-related potentials for real world human-robot interaction. Scientific reports , 7(1):17562, 2017. [9] T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra. Continuous control with deep reinforcement learning. ArXiv e-prints , Sept. 2015. [10] F. Zhang, J. Leitner, M. Milford, B. Upcroft, and P. Corke. Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control. ArXiv e-prints , Nov. 2015. [11] C. Zimmermann and T. Brox. Learning to estimate 3d hand pose from single rgb images. In IEEE International Conference on Computer Vision (ICCV) , 2017. https://arxiv.org/abs/1705.01389.

Future Work

Add mask rcnn tracking for gesture control of robot

About

Deep reinforcement learning applied to a novel 2d environment.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages