Ab sofort ist der Login auf der Weboberfläche von git.fh-muenster.de bevorzugt über FH Muenster SSO möglich.

Commit f0ade70d authored by Daniel Lukats's avatar Daniel Lukats

fixed numerous bibliography entries

parent 2b594398
......@@ -55,7 +55,7 @@
@article{gae,
author = {John Schulman and Philipp Moritz and Sergey Levine and Michael Jordan and Pieter Abbeel},
title = {High-Dimensional Continuous Control Using Generalized Advantage Estimation},
year = 2015,
year = 2016,
journal = {International Conference on Learning Representations},
}
......@@ -64,6 +64,8 @@
and Wojciech Zaremba},
title = {OpenAI Gym},
year = 2016,
journal = {arXiv},
volume = {abs/1606.01540v1},
}
@article{nature_dqn,
......@@ -85,14 +87,18 @@
and Gray, Scott and Olsson, Catherine and Pachocki, Jakub and Petrov, Michael and Pinto, Henrique and
Raiman, Jonathan and Salimans, Tim and Schlatter, Jeremy and Zhang, Susan},
year = {2019},
title = {Dota 2 with Large Scale Deep Reinforcement Learning}
title = {Dota 2 with Large Scale Deep Reinforcement Learning},
journal = {arXiv},
volume = {abs/1912.06680v1},
}
@article{rainbow,
author = {Hessel, Matteo and Modayil, Joseph and Van Hasselt, Hado and Schaul, Tom and Ostrovski, Georg and
Dabney, Will and Horgan, Dan and Piot, Bilal and Azar, Mohammad and Silver, David},
year = {2017},
title = {Rainbow: Combining Improvements in Deep Reinforcement Learning}
title = {Rainbow: Combining Improvements in Deep Reinforcement Learning},
journal = {arXiv},
volume = {abs/1710.02298v1},
}
@article{reinforce,
......@@ -117,12 +123,15 @@
author = {John Schulman and Filip Wolski and Prafulla Dhariwal and Alec Radford and Oleg Klimov},
title = {Proximal Policy Optimization Algorithms},
year = 2017,
journal = {arXiv},
volume = {abs/1707.06347v2},
}
@article{baird1993,
author = {Leemon C. Baird},
title = {Advantage Updating},
year = 1993,
journal = {Wright Laboratory Technical Report},
}
@article{brown2019,
......@@ -134,11 +143,6 @@
pages = {885--890},
}
@article{chen2018,
author = {Shengnan Chen},
title = {Comparing Deep Reinforcement Learning Methods for Engineering Applications},
year = 2018,
}
@article{engstrom2019,
author = {Logan Engstrom and Andrew Ilyas and Shibani Santurkar and Dimitris Tsipras and Firdaus Janoos and Larry
......@@ -148,13 +152,6 @@
year = 2019,
}
@article{gueldenring2019,
author = {Ronja G\"uldenring},
title = {Applying Deep Reinforcement Learning in the Navigation of Mobile Robots in Static and Dynamic
Environments},
year = 2019,
}
@article{houthooft2018,
author = {Rein Houthooft and Yuhua Chen and Phillip Isola and Bradly Stadie and Filip Wolski and Jonathan Ho and
Pieter Abbeel},
......@@ -178,8 +175,9 @@
author = {Andrew Ilyas and Long Engstrom and Shibani Santurkar and Dimitris Tsipras and Firdaus Janoos and Larry
Rudolph and Aleksander Madry},
title = {Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?},
journal = {arXiv preprint},
year = 2018,
journal = {arXiv},
volume = {abs/1811.02553v3},
}
@article{kakade2002,
......@@ -243,6 +241,7 @@
author = {Ian Goodfellow and Yoshua Bengio and Aaron Courville},
publisher = {MIT Press},
year = 2016,
note = {ISBN: 9780262035613},
}
@book{sutton18,
......@@ -251,9 +250,10 @@
publisher = {MIT Press},
year = 2018,
edition = 2,
note = {ISBN: 9780262039246},
}
@online{baselines,
@misc{baselines,
author = {{OpenAI Inc.}},
title = {OpenAI Baselines},
year = 2017,
......@@ -261,7 +261,7 @@
urldate = {2020-03-26},
}
@online{jayasiri,
@misc{jayasiri,
author = {Varuna Jayasiri},
title = {Proximal Policy Optimization Algorithms - PPO in PyTorch},
year = {n.d.},
......@@ -269,7 +269,7 @@
urldate = {2020-05-24},
}
@online{kostrikov,
@misc{kostrikov,
author = {Ilya Kostrikov},
title = {pytorch-a2c-ppo-acktr},
year = 2018,
......@@ -277,7 +277,7 @@
urldate = {2020-05-08},
}
@online{ppo_blog,
@misc{ppo_blog,
author = {{OpenAI Inc.}},
title = {Proximal Policy Optimization},
year = 2017,
......@@ -285,7 +285,7 @@
urldate = {2020-04-30},
}
@online{pytorch,
@misc{pytorch,
author = {{PyTorch Contributors}},
title = {PyTorch 1.5.0 documentation},
year = 2019,
......@@ -293,7 +293,7 @@
urldate = {2020-05-26},
}
@online{seita2017,
@misc{seita2017,
author = {Daniel Seita},
title = {Going Deeper Into Reinforcement Learning: Fundamentals of Policy Gradients},
year = 2017,
......@@ -301,7 +301,7 @@
urldate = {2020-05-04},
}
@online{spinningup,
@misc{spinningup,
author = {{OpenAI Inc.}},
title = {OpenAI Spinning Up},
year = 2018,
......@@ -309,10 +309,31 @@
urldate = {2020-05-04},
}
@online{results,
@misc{results,
author = {Daniel Lukats},
title = {PPO Experiment Findings},
year = 2020,
url = {https://github.com/Aethiles/ppo-results},
urldate = {\today},
}
@mastersthesis{chen2018,
author = {Shengnan Chen},
title = {Comparing Deep Reinforcement Learning Methods for Engineering Applications},
year = 2018,
school = {Otto-von-Guericke-Universit\"at Magdeburg},
url =
{https://www.ci.ovgu.de/is_media/Master+und+Bachelor_Arbeiten/MasterThesis_ShengnanChen_2018-p-4774.pdf},
urldate = {2020-05-29},
}
@mastersthesis{gueldenring2019,
author = {Ronja G\"uldenring},
title = {Applying Deep Reinforcement Learning in the Navigation of Mobile Robots in Static and Dynamic
Environments},
year = 2019,
school = {Universit\"at Hamburg},
url = {https://tams.informatik.uni-hamburg.de/publications/2019/MSc_Ronja_Gueldenring.pdf},
urldate = {2020-05-29},
}
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment