MineDojo/Voyager

UserWarning: Subprocess mineflayer failed to start.

Pioneer-Weirdo opened this issue · 4 comments

Pioneer-Weirdo commented

Loading Skill Manager from ./skill_library/trial1/skill
Mineflayer process has exited, restarting
Subprocess mineflayer started with PID 23100.
E:\code\python\Voyager\voyager\env\process_monitor.py:65: UserWarning: Subprocess mineflayer failed to start.
warnings.warn(f"Subprocess {self.name} failed to start.")
Mineflayer process has exited, restarting
...
.....
....
raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPConnectionPool(host='127.0.0.1', port=3001): Max retries exceeded with url: /start (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000002DB8B2B2B20>: Failed to establish a new connection: [WinError 10061] 由于目标计算机积极拒绝，无法连接。'))

end
Pioneer-Weirdo commented

I'm using Minecraft on my local machine, configured for LAN play, but the Voyager bot has not been able to enter the game, and it keeps showing "Subprocess mineflayer failed to start" in the terminal.

Pioneer-Weirdo commented

This is my configuration.

from voyager import Voyager
# You can also use mc_port instead of azure_login, but azure_login is highly recommended
azure_login = {
    "client_id": "YOUR_CLIENT_ID",
    "redirect_url": "https://127.0.0.1/auth-response",
    "secret_value": "[OPTIONAL] YOUR_SECRET_VALUE",
    "version": "fabric-loader-0.14.18-1.19", # the version Voyager is tested on
}
mc_port='11438'
openai_api_key = "sk-DPF8Yz0l3KFJV0L6TeD5iP6xi1ApHFwhyeX7BsYozpje5cC6Y"

voyager = Voyager(
    # azure_login=azure_login,
    server_port=3001,
    mc_port=mc_port,
    openai_api_key=openai_api_key,
    skill_library_dir="./skill_library/trial1", # Load a learned skill library.
    ckpt_dir="YOUR_CKPT_DIR", # Feel free to use a new dir. Do not use the same dir as skill library because new events will still be recorded to ckpt_dir.
    resume=False, # Do not resume from a skill library because this is not learning.
)

# start lifelong learning
voyager.learn()
github-actions commented

This issue is stale because it has been open for 30 days with no activity.

github-actions commented

This issue was closed because it has been inactive for 14 days since being marked as stale.