def launch(config, distributed_config):
config = convert_dottable(config)
distributed_config = convert_dottable(distributed_config)
env = Env(config.env.scenario, config.env.topology, durations=config.env.durations)
agent_id_list = [str(agent_id) for agent_id in env.agent_idx_list]
state_shaper = CIMStateShaper(**config.env.state_shaping)
action_shaper = CIMActionShaper(action_space=list(np.linspace(-1.0, 1.0, config.agents.algorithm.num_actions)))
experience_shaper = TruncatedExperienceShaper(**config.env.experience_shaping)
config["agents"]["algorithm"]["input_dim"] = state_shaper.dim
agent_manager = DQNAgentManager(
name="cim_actor",
mode=AgentManagerMode.INFERENCE,
agent_dict=create_dqn_agents(agent_id_list, config.agents),
state_shaper=state_shaper,
action_shaper=action_shaper,
experience_shaper=experience_shaper
)
proxy_params = {
"group_name": os.environ["GROUP"] if "GROUP" in os.environ else distributed_config.group,
"expected_peers": {"learner": 1},
"redis_address": (distributed_config.redis.hostname, distributed_config.redis.port),
"max_retries": 15
}
actor_worker = ActorWorker(
local_actor=SimpleActor(env=env, agent_manager=agent_manager),
proxy_params=proxy_params
)
actor_worker.launch()
"epsilon_range_dict": {
"_all_": config.exploration.epsilon_range
},
"split_point_dict": {
"_all_": config.exploration.split_point
},
"with_cache": config.exploration.with_cache
}
explorer = TwoPhaseLinearExplorer(agent_id_list,
config.general.total_training_episodes,
**exploration_config)
agent_manager = DQNAgentManager(name="cim_remote_actor",
agent_id_list=agent_id_list,
mode=AgentMode.INFERENCE,
state_shaper=state_shaper,
action_shaper=action_shaper,
experience_shaper=experience_shaper,
explorer=explorer)
proxy_params = {
"group_name":
config.distributed.group_name,
"expected_peers":
config.distributed.actor.peer,
"redis_address":
(config.distributed.redis.host_name, config.distributed.redis.port)
}
actor_worker = ActorWorker(local_actor=SimpleActor(
env=env, inference_agents=agent_manager),
proxy_params=proxy_params)
actor_worker.launch()