List view

• Implementation of a variety of methods

  No due date

  •0/4 issues closed
  0% complete4 open0 closed

• Example code for basic experimentation framework

  No due date

  •2/4 issues closed
  50% complete2 open2 closed

• Halite Game

  This is a placeholder until we know the game's date. Read up on the documentation, download the starter bots, and start exploring strategies for the game along with a potential wrapper to allow for self-play for large parallel simulations of self-play.

  Overdue by 7 year(s)

  •

  Due by October 31, 2018
  0% complete0 open0 closed

• ELF Testing

  Modifying and Testing our RL algorithms on the ELF workflow to test environments that require a higher level of strategy or planning such as RTS or Capture the Flag. This will better prepare us for strategizing during Halite since we would come up with our own hardcoded bots, strategies, potential changing of rewards etc.

  Overdue by 7 year(s)

  •

  Due by October 10, 2018
  0% complete0 open0 closed

• Completion of OpenAI Env

  The RL algorithm is complete, thoroughly tested on an OpenAI environment (record some videos for demos or future slides!). At this point, we should have an in-depth understanding of an RL algorithm along with a general idea of its pros and cons.

  Overdue by 7 year(s)

  •

  Due by September 29, 2018

  •1/1 issues closed
  100% complete0 open1 closed

• Near Complete Implementation

  The algortithm by this point should be hopefully complete and fully functional on an environment of your choosing. If not, make sure the implementation is done with only a bug causing issues in the loss or gradient.

  Overdue by 7 year(s)

  •

  Due by September 25, 2018
  0% complete0 open0 closed