Change way action space is discretized #205
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Was PR #176 related to issue #175 which was closed
This commit change the way a Box action is discretized.
It is inspired from the gym.spaces.Box.sample method. For unbounded spaces it builds on the quantile distribution of the Cauchy distribution (using a scale of 1).
An alternative could be derived from the logit function: log(1+p) - log(1-p) for example. But the current implementation has a larger spread.