[question] for an RL algorithm with a discrete action space, is it possible to get a probability of outcomes when feeding in data?

hill-a / stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

http://stable-baselines.readthedocs.io/

MIT License

4.16k stars 725 forks source link

[question] for an RL algorithm with a discrete action space, is it possible to get a probability of outcomes when feeding in data? #1171

Open george-adams1 opened 2 years ago

george-adams1 commented 2 years ago

For example, if I feed in data to an RL algorithm with possible actions up or down, is it possible to know for every frame what the probability is that the model is going to pick up or down?