Fun with reinformcent learning - TT DevDays Berlin 2018

Quick Test Rig Hacks

fix /usr/lib/python3.4/site-packages/rl/callbacks.py

References

  1. https://yanpanlau.github.io/2016/10/11/Torcs-Keras.html

  2. https://selfdrivingcars.mit.edu/

  3. https://www.slideshare.net/SnehaRavikumar1/reinforcement-learning-for-self-driving-cars

  4. https://keras.io/

  5. https://github.com/openai/gym

  6. https://github.com/ugo-nama-kun/gym_torcs

  7. https://github.com/imagry/Gym-Torcs-DQN

  8. Learning to Predict by the Methods of Temporal Differences

  9. Learning from delayed rewards

  10. Human-level control through deep reinforcement learning

  11. Playing Atari with Deep Reinforcement Learning

  12. Deep Reinforcement Learning with Double Q-learning

  13. Dueling Network Architectures for Deep Reinforcement Learning

  14. Continuous control with deep reinforcement learning