RLLib: self_play_league_based_with_open_spiel.py about ray HOT 1 OPEN

ppo_config = (
                PPOConfig()
                .environment(MultiAgentCartPole, env_config={"num_agents": 2})
                # Switch both the new API stack flags to True (both False by default).
                # This enables the use of:
                # a) RLModule (replaces ModelV2) and Learner (replaces Policy)
                # b) and automatically picks the correct EnvRunner (single-agent vs multi-agent) and enables ConnectorV2 support.
                .api_stack(
                    enable_rl_module_and_learner=True,
                    enable_env_runner_and_connector_v2=True,
                )
                .resources(
                    num_cpus_for_main_process=16,
                )
                # supports arbitrary scaling on the learner axis, feel free to set
                # `num_learners` to the number of available GPUs for multi-GPU training (and `num_gpus_per_learner=1`).
                .learners(
                    num_learners=0,  # <- set this value to the number of GPUs
                    num_gpus_per_learner=0,  # <- set this to 1, if you have a GPU
                )
                .training(train_batch_size_per_learner=5000)
                # Because you are in a multi-agent env, you have to set up the usual multi-agent parameters:
                .multi_agent(
                    policies={"p0", "p1"},
                    # Map agent 0 to p0 and agent 1 to p1.
                    policy_mapping_fn=lambda agent_id, episode, **kwargs: f"p{agent_id}",
                    policies_to_train=["p0"],
                )
            )