Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
This release brings in deprecating changes to the core `env.step()` routine, and lays the groundwork for enabling new types of compiler optimizations to be exposed through CompilerGym. Many thanks to code contributors: @mostafaelhoushi, @sogartar, @KyleHerndon, @uduse, @parthchadha, and @xtremey! Highlights of this release include: - Added a new TextSizeInBytes observation space for LLVM. - Added a new PPO leaderboard entry - Fixed a bug in which temporary directories created by the LLVM environment were not cleaned up. - The function createAndRunCompilerGymService() now returns an int, which is the exit return code. - Improvements to the examples documentation and FAQ. Deprecations and breaking changes: - CompilerEnv.step no longer accepts a list of actions. A new method, CompilerEnv.multistep provides this functionality. This is to provide compatibility with environments whose action spaces are lists. To update your code, replace any calls to env.step() which take a list of actions to use env.multistep(). - The arguments observations and rewards to step() have been renamed observation_spaces and reward_spaces, respectively. - Reward.id has been renamed Reward.name. - The backend protocol buffer schema has been updated to natively support more types of observation and action, and to support nested spaces.
- Loading branch information