search

itu-square / symsim

SQUARE Symsim is a test-bed for implementing reinforcement learning algorithms, formalizing their correctness properties, and testing them. It is implemented in Scala 3, in purely functional style, and uses property-based testing.
Apache License 2.0
2 stars 0 forks source link

Pole balancing agent Example 3.3 #CartPole #22

Open wasowski opened 3 years ago

wasowski commented 3 years ago

p. 56 [78] OpenAI has an implementation, as probably also for many other examples from this book. https://github.com/openai/gym/blob/master/gym/envs/classic_control/cartpole.py https://gym.openai.com/envs/CartPole-v1/

wasowski commented 1 year ago

A. G. Barto, R. S. Sutton, and C. W. Anderson, “Neu- ronlike adaptive elements that can solve difficult learning control problems,” IEEE transactions on systems, man, and cybernetics, no. 5, pp. 834–846, 1983.

https://github.com/openai/gym/blob/master/gym/envs/classic_control/cartpole.py

Perhaps add DRL first.

(the above moved from issue #22)