algorithm: PPO

# Multi-agent-env setting:
# If true:
# - Any AIController with done = true will receive zeroes as action values until all AIControllers are done, an episode ends at that point.
# - ai_controller.needs_reset will also be set to true every time a new episode begins (but you can ignore it in your env if needed).
# If false:
# - AIControllers auto-reset in Godot and will receive actions after setting done = true.
# - Each AIController has its own episodes that can end/reset at any point.
# Set to false if you have a single policy name for all agents set in AIControllers
env_is_multiagent: false

checkpoint_frequency: 20

# You can set one or more stopping criteria
stop:
    #episode_reward_mean: 0
    #training_iteration: 1000
    #timesteps_total: 10000
    time_total_s: 10000000

config:
    env: godot
    env_config:
        env_path: '/home/valapeos/Projects/pneumarl/pneuma.x86_64' # Set your env path here (exported executable from Godot) - e.g. env_path: 'env_path.exe' on Windows
        action_repeat: null # Doesn't need to be set here, you can set this in sync node in Godot editor as well
        show_window: true # Displays game window while training. Might be faster when false in some cases, turning off also reduces GPU usage if you don't need rendering.
        speedup: 30 # Speeds up Godot physics

    framework: torch # ONNX models exported with torch are compatible with the current Godot RL Agents Plugin

    lr: 0.0003
    lambda: 0.95
    gamma: 0.99

    vf_loss_coeff: 0.5
    vf_clip_param: .inf
    #clip_param: 0.2
    entropy_coeff: 0.0001
    entropy_coeff_schedule: null
    #grad_clip: 0.5

    normalize_actions: False
    clip_actions: True # During onnx inference we simply clip the actions to [-1.0, 1.0] range, set here to match

    rollout_fragment_length: 32
    sgd_minibatch_size: 128
    num_workers: 4
    num_envs_per_worker: 1 # This will be set automatically if not multi-agent. If multi-agent, changing this changes how many envs to launch per worker.
    # The value below needs changing per env
    # Basic calculation for this value can be rollout_fragment_length * num_workers * num_envs_per_worker (how many AIControllers you have if not multi_agent, otherwise the value you set)
    train_batch_size: 2048 

    num_sgd_iter: 4
    batch_mode: truncate_episodes

    num_gpus: 0
    model:
        vf_share_layers: False
        fcnet_hiddens: [64, 64]