datamllab / rlcard

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

Home Page:http://www.rlcard.org

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Code correction for run_rl.py

billh0420 opened this issue · comments

Lines 37-40 of run_rl.py are:

`

        agents = [agent]

        for _ in range(env.num_players):

                agents.append(RandomAgent(num_actions=env.num_actions))

         env.set_agents(agents)

`

There is an extra randomAgent being added.

A correction could be:

`

        agents = [agent]

        for _ in range(1, env.num_players):

                agents.append(RandomAgent(num_actions=env.num_actions))

        env.set_agents(agents)

`

Thanks for letting us know! It is fixed.