Commit 4685f9d4 authored by Daniel Lukats's avatar Daniel Lukats

added two theses, curiosity and rainbow dqn

parent 614ec44d
......@@ -88,6 +88,13 @@
title = {Dota 2 with Large Scale Deep Reinforcement Learning}
}
@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}
}
@article{reinforce,
author = {Ronald J. Williams},
title = {Simple statistical gradient-following algorithms for connectionist reinforcement learning},
......@@ -127,6 +134,12 @@
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
Rudolph and Aleksander Madry},
......@@ -135,6 +148,13 @@
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},
......@@ -170,6 +190,21 @@
volume = 19,
}
@article{nasa,
author = {Daniel Miller and Jacob A. Englander and Richard Linares},
title = {Interplanetary Low-Thrust Design Using Proximal Policy Optimization},
year = 2019,
journal = {AAS/AIAA Astrodynamics Specialist Conference},
}
@article{pathak2017,
author = {Deepak Pathak and Pulkit Agrawal and Alexei A. Efros and Trevor Darrell},
title = {Curiosity-driven Exploration by Self-supervised Prediction},
year = 2017,
journal = {International Conference on Machine Learning},
volume = 34,
}
@article{peng2018,
author = {Peng, Xue Bin and Abbeel, Pieter and Levine, Sergey and van de Panne, Michiel},
title = {DeepMimic: Example-guided Deep Reinforcement Learning of Physics-based Character Skills},
......@@ -221,11 +256,19 @@
@online{baselines,
author = {{OpenAI Inc.}},
title = {OpenAI Baselines},
year = 2020,
year = 2017,
url = {https://github.com/openai/baselines},
urldate = {2020-03-26},
}
@online{jayasiri,
author = {Varuna Jayasiri},
title = {Proximal Policy Optimization Algorithms - PPO in PyTorch},
year = {n.d.},
url = {https://blog.varunajayasiri.com/ml/ppo_pytorch.html},
urldate = {2020-05-24},
}
@online{kostrikov,
author = {Ilya Kostrikov},
title = {pytorch-a2c-ppo-acktr},
......@@ -242,6 +285,14 @@
urldate = {2020-04-30},
}
@online{pytorch,
author = {{PyTorch Contributors}},
title = {PyTorch 1.5.0 documentation},
year = 2019,
url = {https://pytorch.org/docs/stable/notes/randomness.html},
urldate = {2020-05-26},
}
@online{seita2017,
author = {Daniel Seita},
title = {Going Deeper Into Reinforcement Learning: Fundamentals of Policy Gradients},
......
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