An OpenAI Gym environment for Gambling problems
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.


The Gambling environment is a single agent domain featuring discrete and continuous state and action spaces. Currently, one task is supported:


This environment corresponds to the version of the gambling problem described in Example 1.2 in Algorithms for Reinforcement Learning by Csaba Szepesvari (2010).

Future tasks

Future tasks will have more complex environments that an agent can plan such as:

  • Blackjack
  • Poker
  • Roulette
  • Slots
  • Eucher


cd gym-gambling
pip install -e .