New answers tagged discrete-action-spaces
0
votes
PPO: multiple discrete actions per step, one depends on the other
What you describe will be possible, but you need to ensure that your policy returns the probability of the action(s) taken.
In the two step process you describe, you would have something like
\begin{...
Top 50 recent answers are included
Related Tags
reinforcement-learning × 8discrete-action-spaces × 8
continuous-action-spaces × 3
deep-rl × 2
proximal-policy-optimization × 2
action-spaces × 2
dqn × 1
objective-functions × 1
markov-decision-process × 1
reinforce × 1
state-spaces × 1
multi-agent-rl × 1
multi-action-rl × 1