0

I am trying to train an AI with an environment where the states are continuous but the actions are discrete, that means I can not apply DDPG or TD3.

Can someone please help to let know what should be the best algorithm for discrete action spaces and is there any version of DDPG or TD3 which can be applied to discrete action spaces on partially observable MDPs.

nbro
  • 39,006
  • 12
  • 98
  • 176
user2783767
  • 121
  • 2
  • there are lots of options you can choose from! You might want to start with vanilla DQN and then see if you can use any variants to improve upon this. The same with actor-critic. I usually like to start with the simplest model for my problem and then adapt it until it works. – David Aug 07 '20 at 09:00
  • 1
    This resource gives an interactive guide on selection of RL algorithms. https://intellabs.github.io/coach/selecting_an_algorithm.html It might not give a direct answer for this particular case, but can be useful – mugoh Nov 15 '20 at 07:14
  • Hi there i saw recently this question, i would like to know if you reached your goal and found a way to use TD3 also in pomdp environments and discrete action space. – Smaike94 May 02 '22 at 09:40
  • Hi TD3 is not for discrete action space..I found the best solution as r2d2...you can check any good github RL dipository for this. – user2783767 May 04 '22 at 01:30

0 Answers0