For custom env about mobile-env HOT 4 CLOSED

import gymnasium
from ray.tune.registry import register_env

# use the mobile-env RLlib wrapper for RLlib
def register(config):
    # importing mobile_env registers the included environments
    import mobile_env
    from mobile_env.wrappers.multi_agent import RLlibMAWrapper

    env = gymnasium.make("mobile-small-ma-v0")
    return RLlibMAWrapper(env)

# register the predefined scenario with RLlib
register_env("mobile-small-ma-v0", register)

import ray

# init ray with available CPUs (and GPUs) and init ray
ray.init(
  num_cpus=5,   # change to your available number of CPUs
  include_dashboard=False,
  ignore_reinit_error=True,
  log_to_driver=False,
)

import ray.air
from ray.rllib.algorithms.ppo import PPOConfig

from ray.rllib.policy.policy import PolicySpec
from ray.tune.stopper import MaximumIterationStopper

# Create an RLlib config using multi-agent PPO on mobile-env's small scenario.
config = (
    PPOConfig()
    .environment(env="mobile-small-ma-v0")
    # Here, we configure all agents to share the same policy.
    .multi_agent(
        policies={'shared_policy': PolicySpec()},
        policy_mapping_fn=lambda agent_id, episode, worker, **kwargs: 'shared_policy',
    )
    # RLlib needs +1 CPU than configured below (for the driver/traininer?)
    .resources(num_cpus_per_worker=4)
    .rollouts(num_rollout_workers=1)
)

# Create the Trainer/Tuner and define how long to train
tuner = ray.tune.Tuner(
    "PPO",
    run_config=ray.air.RunConfig(
        # Save the training progress and checkpoints locally under the specified subfolder.
        storage_path="./CTDE_1m",
        # Control training length by setting the number of iterations. 1 iter = 4000 time steps by default.
        stop=MaximumIterationStopper(max_iter=1),
        checkpoint_config=ray.air.CheckpointConfig(checkpoint_at_end=True),
    ),
    param_space=config,
)

# Run training and save the result
result_grid = tuner.fit()

from ray.tune.registry import register_env

# use the mobile-env RLlib wrapper for RLlib
def register(config):
    # importing mobile_env registers the included environments
    from mobile_env.wrappers.multi_agent import RLlibMAWrapper

    env = Env1(config={"seed": 68},render_mode="rgb_array")
    return RLlibMAWrapper(env)

# register the predefined scenario with RLlib
register_env("TEST1", register)