Doom

Tues gitlab: https://gitlab.gbar.dtu.dk/tuhe/02460_doom_rl_2019/tree/master

Alex' Deep learning: https://docs.google.com/document/d/1SY04zKiqyohsy2idU-jUDWvL0sUMSuNaRlH8QfHo3HY/edit#

Deep learning kurset: https://docs.google.com/document/d/1UYpSF3FguEDg_AT3Vtczj5-DAjdICyHEA3L4KQIOPjo/edit?fbclid=IwAR0HKROVU-BClrNxKcu2RU-7r95_oordz5cKxXM_pX4__vbh6vcKdDPawZQ#heading=h.82pny4w29n7h

Ole's videoer: https://www.youtube.com/playlist?list=PLHEFRBAk3vdLrOnirtNWp1h1U8ZLZOWXP

Deep learning bogen: http://www.deeplearningbook.org/

Berkeley: http://rail.eecs.berkeley.edu/deeprlcourse/

Openai: https://spinningup.openai.com/en/latest/index.html

Carnegie Mellon University: PGM, Deep Learning & Reinforcement Learning i ét kursus: https://sailinglab.github.io/pgm-spring-2019/lectures/ Se projekterne også: https://sailinglab.github.io/pgm-spring-2019/project/

General articles:

ViZDoom Competitions: Playing Doom from Pixels: https://arxiv.org/pdf/1809.03470.pdf HIGH-DIMENSIONAL CONTINUOUS CONTROL USING GENERALIZED ADVANTAGE ESTIMATION: https://arxiv.org/pdf/1506.02438.pdf

Deep Q:

https://arxiv.org/pdf/1609.05521.pdf

https://flyyufelix.github.io/2017/10/12/dqn-vs-pg.html

https://arxiv.org/pdf/1511.06581.pdf

Policy gradient:

An introduction to Policy Gradients with Cartpole and Doom: https://medium.freecodecamp.org/an-introduction-to-policy-gradients-with-cartpole-and-doom-495b5ef2207f ...and code: https://github.com/simoninithomas/Deep_reinforcement_learning_Course/tree/master/Policy%20Gradients

Deterministic Policy Gradient Algorithms (DeepMind) http://proceedings.mlr.press/v32/silver14.pdf

Actor critic:

TRAINING AGENT FOR FIRST-PERSON SHOOTER GAME WITH ACTOR-CRITIC CURRICULUM LEARNING: https://openreview.net/pdf?id=Hk3mPK5gg

Asynchronous Actor-Critic Agents (A3C): https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-8-asynchronous-actor-critic-agents-a3c-c88f72a5e9f2

Google paper - Asynchronous Methods for Deep Reinforcement Learning: https://arxiv.org/pdf/1602.01783.pdf

Automated Curriculum Learning by Rewarding Temporally Rare Events: https://njustesen.files.wordpress.com/2018/06/justesen2018automated.pdf

Miscellaneous:

https://github.com/ppaquette/gym-doom

https://gym.openai.com/envs/DoomCorridor-v0/

https://www.codelitt.com/blog/doom-ai2/