7 votes
Accepted

How to implement a variable action space in Proximal Policy Optimization?

The most straightforward solution is to simply make every action "legal", but implementing a consistent, deterministic mapping from potentially illegal actions to different legal actions. Whenever the ...
user avatar
  • 9,429
6 votes
Accepted

What techniques are used to make MDP discrete state space manageable?

tl:dr Read chapter 9 of an Introduction of Reinforcement Learning There is definitely a problem (a curse if you will) when the dimensionality of a task (MDP) grows. For fun, lets extend your problem ...
user avatar
4 votes
Accepted

Can a large discrete action space be represented using Gaussian distributions?

The answer is "it depends". Once you have arranged the actions into order, a key trait is whether the action value function has a simple enough shape that sampling from a Gaussian policy ...
user avatar
  • 24.5k
2 votes

How to implement a variable action space in Proximal Policy Optimization?

Change the action space at each step, depending on the internal_state. I assume this is nonsense. Yes, this seems overkill and makes the problem unnecessarily complex, there could be other things ...
user avatar
1 vote

Is there a multi-agent deep reinforcement learning algorithm which is for environments with only discrete action spaces (Not hybrid)?

A natural policy to act in an environment with discrete action space would be a softmax. This paper describes a method that uses the idea of centralized training, and I believe could be used in your ...
user avatar
1 vote

How to implement a variable action space in Proximal Policy Optimization?

Normally, the set of actions that the agent can execute does not change over time, but some actions can become impossible in different states (for example, not every move is possible in any position ...
user avatar

Only top scored, non community-wiki answers of a minimum length are eligible