I am getting this error in trying to use the built in examples in external env. Has anyone seen these?
On the server side using the cartpole_server.py
PPO pid=36536) 2025-01-06 21:00:50,783 WARNING ppo.py:295 -- You are running PPO on the new API stack! This is the new default behavior for this algorithm. If you don't want to use the new API stack, set `config.api_stack(enable_rl_module_and_learner=False,enable_env_runner_and_connector_v2=False)`. For a detailed migration guide, see here: https://docs.ray.io/en/master/rllib/new-api-stack-migration-guide.html
(PPO pid=36536) 2025-01-06 21:00:54,766 ERROR actor_manager.py:804 -- Ray error (The actor died because of an error raised in its creation task, ray::SingleAgentEnvRunner.__init__() (pid=36538, ip=127.0.0.1, actor_id=6bec1618192ff30633cca45801000000, repr=<ray.rllib.env.single_agent_env_runner.SingleAgentEnvRunner object at 0x1a719fed0>)
(PPO pid=36536) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(PPO pid=36536) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(PPO pid=36536) File "/opt/anaconda3/lib/python3.11/site-packages/ray/rllib/env/single_agent_env_runner.py", line 89, in __init__
(PPO pid=36536) self.make_env()
(PPO pid=36536) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(PPO pid=36536) File "/opt/anaconda3/lib/python3.11/site-packages/ray/rllib/env/single_agent_env_runner.py", line 604, in make_env
(PPO pid=36536) raise ValueError(
(PPO pid=36536) ValueError: `config.env` is not provided! You should provide a valid environment to your config through `config.environment([env descriptor e.g. 'CartPole-v1'])`.), taking actor 1 out of service.
I am also getting this error on the client side using the cartpole_client.py
llib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0x1510de910>: Failed to establish a new connection: [Errno 61] Connection refused