Resource Dump

All Resources

DeepMimic

• [Paper] DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
  • https://xbpeng.github.io/projects/DeepMimic/index.html
• Proximal Policy Optimization Algorithms
  • https://arxiv.org/abs/1707.06347
• A Comprehensive Guide to Machine Learning
  • http://snasiriany.me/files/ml-book.pdf
• Xue Bin (Jason) Peng: Towards a Virtual Stuntman
  • https://bair.berkeley.edu/blog/2018/04/10/virtual-stuntman/
• SIGGRAPH 2018: DeepMimic paper (main video)
  • https://youtu.be/vppFvq2quQ0

Policy Gradients

• (DDPG) Continuous Control with Deep Reinforcement Learning
  • https://arxiv.org/abs/1509.02971
• Stack Exchange: When can we interchange integration and differentiation?
  • https://math.stackexchange.com/questions/2530213/when-can-we-interchange-integration-and-differentiation
• Daniel Takeshi: Going Deeper Into Reinforcement Learning: Fundamentals of Policy Gradients
  • https://danieltakeshi.github.io/2017/03/28/going-deeper-into-reinforcement-learning-fundamentals-of-policy-gradients/

On Policy vs. Off Policy

• Stack Overflow explanation of On vs Off Policy
  • https://stats.stackexchange.com/a/184794
• Simple Explanation of On-Policy Q-Learning and Off-Policy SARSA
  • https://www.cse.unsw.edu.au/~cs9417ml/RL1/algorithms.html
• Action policies: $\epsilon$-greedy, $\epsilon$-soft, softmax
  • https://www.cse.unsw.edu.au/~cs9417ml/RL1/tdlearning.html#aselection
• Q-Learning and SARSA Algorithm pseudo code:
  • https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-i-q-learning-sarsa-dqn-ddpg-72a5e0cb6287

Textbooks

• Sutton and Barto’s “Reinforcement Learning: An Introduction” Book
  • http://incompleteideas.net/book/bookdraft2017nov5.pdf
• A Comprehensive Guide to Machine Learning
  • http://snasiriany.me/files/ml-book.pdf