wenkesj / holdem

:black_joker: OpenAI Gym No Limit Texas Hold 'em Environment for Reinforcement Learning
162 stars 62 forks source link

openai/gym commit #836 change spec #1

Closed traderbagel closed 6 years ago

traderbagel commented 6 years ago

according to commit message

  • Changed MultiDiscrete action space to range from [0, ..., n-1] rather than [a, ..., b-1].

this cause the current code can't run.

wenkesj commented 6 years ago

2 should fix this but would like to support the other changes from that release