Study papers

[abhinavagarwal07]

http://www.ias.tu-darmstadt.de/uploads/Publications/Kober_IJRR_2013.pdf

https://en.wikipedia.org/wiki/State-Action-Reward-State-Action

[abhinavagarwalla]

For Policy Search Using Evolution Strategy

1. CMA-ES Tutorial: http://arxiv.org/pdf/1604.00772v1.pdf
2. Understanding RL vs BBO: http://www.isir.upmc.fr/files/2013ACTN2859.pdf
3. NAC vs CMA-ES: http://image.diku.dk/igel/paper/VMRLMAttNMCP.pdf
4. Tic-Tac-Toe Example (Training a NN using TDLvsCMA-ES): http://www.gm.fh-koeln.de/~konen/Publikationen/evo-reinforce-GECCO2009.pdf
5. General link for Evolutionary in RL: https://staff.fnwi.uva.nl/s.a.whiteson/pubs/whitesonrlsota11.pdf

[kumarkrishna]

For Deep Reinforcement Learning :

• A Simple Reinforcement Learning Algorithm For Biped Walking
• Reinforcement Learning in Robotics: A Survey
• Deep Q-Learning for Humanoid Walking

Transfer Learning :

• Combining Model-Based Policy Search with Online Model Learning for Control of Physical Humanoids

Language for interaction :

• Learning Language Games through Interaction

[abhinavagarwalla]

1. Benchmarking DRL for continuous control
2. Really good blog post