Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Continuous-mode use/attack don't give correct rewards in multi-agent missions. #303

Closed
timhutton opened this issue Aug 25, 2016 · 1 comment
Labels
Milestone

Comments

@timhutton
Copy link
Contributor

timhutton commented Aug 25, 2016

The second half of two_diggers.py (currently on #302) is failing because the agents get rewards of 2 and 0, instead of 11 and 110.

Problem 1: Rewards for collecting item are all being sent to the first client, in continuous mode.
Problem 2: Rewards for discarding item are not being triggered at all when placing an item in continuous mode. (As with the discrete case, to avoid reward loopholes where an agent repeatedly gets the reward for collecting by placing and digging, we need use to trigger the discarding reward.)

@timhutton timhutton added this to the Elk milestone Aug 25, 2016
@timhutton timhutton added the P2 label Aug 25, 2016
@timhutton timhutton changed the title Rewards for picking item all being sent to the first client, in continuous mode. Continuous-mode use/attack don't give correct rewards in multi-agent missions. Aug 25, 2016
@timhutton
Copy link
Contributor Author

timhutton commented Aug 26, 2016

Looks like EntityItemPickupEvent is server-side only. link

Suggestion is to use ItemPickupEvent instead. Update: no, is server-side too.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

1 participant