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

Brandon/update minerl #20

Open
wants to merge 56 commits into
base: master
Choose a base branch
from
Open

Conversation

brandonhoughton
Copy link
Member

Update Malmo master from dev branch

MadcowD and others added 30 commits April 30, 2019 17:30
Added environment MineRLNavigateExtreme-v0
Added environment MineRLNavigateExtremeDense-v0
Changed compass randomization to reflect human experiment parameters
Added fixed_surface placement type for navigation decorator
* code changes

* Merge branch 'master' into inventory

* schema changes

* add mission.xsd changes; get sample to run

* amount should be 1

* regain backwards compatibility

* code review comment

* Added ObtainIronPickaxe and ObtainDiamond environments
Added updated sample.py to demonstrate dict action space
Added debug statements to enum gym space
Added support for string and integer enum values
Needs testing:
Quit handlers; craft, smeltNearby, craftNearby handlers;

* Added debug env to test handlers

* Fixed CameraCommandsImplementation capturing other commands
CameraCommandsImplementation should return true iff the command should
should be captured. Modified un-matched case to return false

* Remove debug statement

* Added equip handler for inventory abstraction

* Added equip handler

* Revert schema header

* Added equip handler, fixed nearbyCraft and nearbySmelt handlers
Updated quick_start test to demonstrate these features

* Fixed behavior of place command
MadcowD and others added 26 commits June 25, 2019 11:08
* Add randomized spawning to agent start conditions

* Used fixed random bounds for randomized spawn

* debug

* Working randomized start location

* Update randomization region to be larger

* Remove old method of randomly teleporting agent

* Add getTopSolid block method to position helper

* Prevent double reward for log2
Fix issue with random teleportation location

* Updated documentation
* Add randomized spawning to agent start conditions

* Used fixed random bounds for randomized spawn

* debug

* Working randomized start location

* Update randomization region to be larger

* Remove old method of randomly teleporting agent

* Add getTopSolid block method to position helper

* Prevent double reward for log2
Fix issue with random teleportation location

* Updated documentation

* Updated RewardForPossesingItem to fix reward loop and dense behavior

* Remove block comments

* Remove block comments

* Address comments in code review
Update gradle-wrapper.properties to modern gradle
Remove internal print statments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants