New
May 2018 release
New Levels:
-
DMLab-30.
- contributed/dmlab30/psychlab_arbitrary_visuomotor_mapping
- contributed/dmlab30/psychlab_continuous_recognition
-
Psychlab.
- contributed/psychlab/arbitrary_visuomotor_mapping
- contributed/psychlab/continuous_recognition
New Features:
- Support for level caching for improved performance in the Python module.
- Add the ability to spawn pickups dynamically at arbitrary locations.
- Add implementations to read datasets including Cifar10 and Stimuli.
- Add the ability to specify custom actions via 'customDiscreteActionSpec' and 'customDiscreteAction' callbacks.
Bug Fixes:
- Fix playerId and otherPlayerId out by one errors in 'game_rewards.lua'.
- Require playerId passed to
game:addScoreto be one indexed instead of zero indexed and allowgame:addScoreto be used without a playerId. game:renderCustomViewnow renders the view with top-left as the origin. The previous behaviour can be achieved by calling reverse(1) on the returned tensor.