How to apply action masks in HPPO

[battery7]

• I have marked all applicable categories:
  • exception-raising bug
  • RL algorithm bug
  • system worker bug
  • system utils bug
  • code design/refactor
  • documentation request
  • new feature request
• I have visited the readme and doc
• I have searched through the issue tracker and pr tracker
• I have mentioned version numbers, operating system and environment, where applicable:

  import ding, torch, sys
  print(ding.__version__, torch.__version__, sys.version, sys.platform)

[PaParaZz1]

Regarding the "action mask" you mentioned, could you clarify which of the following two types it refers to?

• the mask between different action types (discrete) and action args (continuous)
• the mask about discrete action types at different timesteps

[battery7]

the mask about discrete action types at different timesteps