0

I'm looking for an example-based answer, whether that's code directly in the answer or a link to a tutorial, but regardless more than a text-only answer.

I'm curious- how would one define an arbitrary Markov Decision Process in OpenAI Gym for purposes of reinforcement learning solutions? The sort of problem I see frequently in my role are traveling salesman, vehicle routing, and inventory optimization. Typically, I've used optimization techniques like genetic algorithms and bayesian optimization to find near optimal solutions. However, in this question, I'd like to see a practical/feasible RL approach to such problems. It's my understanding that OpenAI Gym is the simplest tool for defining an agent/environment for RL. (If this is not true, please answer this question with same level of detail using your preferred alternative.)

jbuddy_13
  • 902
  • 2
  • 12
  • 34
  • I made my own codebase for RL. Defining an environment is not really that hard tbh. All the OpenAI can do for you is to force a specific interface on you, thats it. You can manage to do that yourself. – Captain Trojan Jun 20 '21 at 18:34
  • @CaptainTrojan, is your code base on GitHub, PyPi, etc / would you link? – jbuddy_13 Jun 20 '21 at 18:42
  • Sorry, it's proprietary. I use it for courses for my students, so I cannot release it to public. – Captain Trojan Jun 20 '21 at 18:53

0 Answers0