I just read the docs for reinforcement learning purposes, and I think there may be a typo in the OpenAI Gym wrapper example at https://github.com/hsahovic/poke-env/blob/master/examples/rl_with_open_ai_gym_wrapper.py#L36, which is shown in the docs. If you want to account for the number of remaining Pokémons in both parties, shouldn't you filter for if not mon.fainted?
I just read the docs for reinforcement learning purposes, and I think there may be a typo in the OpenAI Gym wrapper example at https://github.com/hsahovic/poke-env/blob/master/examples/rl_with_open_ai_gym_wrapper.py#L36, which is shown in the docs. If you want to account for the number of remaining Pokémons in both parties, shouldn't you filter for
if not mon.fainted
?