o
    ci
                  	   @   s  d dl mZmZmZmZmZ d dlmZ d dlm	Z	 d dl
mZ d dlmZ d dlmZmZ d dlmZ edd	d
Zejdd edkre Zdd Zejd krYeddd  neddd  eej jdeeeedddeddgedddeddgeddddd jed!jd"d#d$Zejd krejd%d& e ejD d'd d( ejd)krejd*d+d,d- eee d.S d.S )/    )DictTupleBoxDiscreteMultiDiscrete)register_env)FlattenObservations)%MultiAgentNestedSpaceRepeatAfterMeEnvNestedSpaceRepeatAfterMeEnv)add_rllib_example_script_args#run_rllib_example_script_experiment)get_trainable_clsi@ g     @)default_timestepsdefault_rewardT)enable_new_api_stack__main__c                 C   s   t tjdkdS )Nr   )multi_agent)r   args
num_agents)envspacesdevice r   c/home/ubuntu/.local/lib/python3.10/site-packages/ray/rllib/examples/actions/nested_action_spaces.py_env_to_module_pipeline   s   r   r   c                 C   s   t t| fi dtjidS )Nr   )config)r	   dictr   r   cr   r   r   <lambda>"   s    r    c                 C   s   t | S )Nr
   r   r   r   r   r    '   s    g      .g      @r      )deg      $g      $@)   r$   )abr   r"   d   )spaceepisode_len)
env_config)env_to_module_connectorg        gMb@?)gammalrc                 C   s   h | ]}d | qS )pr   ).0ir   r   r   	<setcomp>H   s    r1   c                 O   s
   d|  S )Nr.   r   )aidr%   kwr   r   r   r    I   s   
 )policiespolicy_mapping_fnPPOg-C6
?   g{Gz?)entropy_coeff
num_epochsvf_loss_coeffN)!gymnasium.spacesr   r   r   r   r   ray.tune.registryr   "ray.rllib.connectors.env_to_moduler   +ray.rllib.examples.envs.classes.multi_agentr	   @ray.rllib.examples.envs.classes.nested_space_repeat_after_me_envr   ray.rllib.utils.test_utilsr   r   r   parserset_defaults__name__
parse_argsr   r   r   algoget_default_configenvironmentenv_runnerstrainingbase_configr   ranger   r   r   r   <module>   sl    





