config_d.yaml

# Create config.yaml file to overwrite default settings

# General settings
loglevel: info

# Redis settings
redis_address: localhost

local:

# Environment information
env:
  name: SoulsGymIudex-v0
  vectorize: False
  kwargs:
    game_speed: 1.
  obs_shape: [74]
  n_actions: 20
  wrappers:
    IudexObservationWrapper:
      kwargs:

max_env_steps: null

# Algorithm choice
algorithm: DQN

# DQN parameters
dqn:
  batch_size: 64
  train_epochs: 25
  update_samples: 25
  fill_buffer: False
  min_samples: null
  max_model_delay: 10

  agent:
    type: DQNAgent
    kwargs:
      lr: 0.001
      gamma: 0.99
      multistep: 4
      grad_clip: 1.
      q_clip: 2
      device: cuda

  network:
    type: DQN
    kwargs:
      input_dims: 74
      output_dims: 20
      layer_dims: 128

  replay_buffer:
    type: ReplayBuffer
    kwargs:
      max_size: 100_000

  observation_transform:
    type: Normalize
    kwargs:
      keys:
        - obs
      shapes:
        - [8]

  value_transform:
    type: Chain
    kwargs:
      transforms:
        - type: Mask
          kwargs:
            key: __value__
            mask_key: [info, action_mask]
        - type: GreedyAction
          kwargs:
            value_key: __value__
            action_key: action

  action_transform:
    type: Choice
    kwargs:
      key: action
      probs: [0.9, 0.1]
      transforms:
        - type: Identity
        - type: ReplaceWithNoise
          kwargs:
            key: action
            noise:
              type: MaskedDiscreteNoise
              kwargs:
                mask_key: [info, action_mask]
                size_n: 20

# Training node settings
checkpoint:
  save: False
  epochs: 100  # Checkpoint every 100th iteration
  save_buffer: False
  load: False
  load_buffer: False
  load_config: False

# Telemetry node settings
telemetry:
  update_interval: 5
  moving_average: 20
  transforms:
    - type: MetricByKey
      kwargs:
        key: ep_reward
        name: rewards
    - type: MetricByKey
      kwargs:
        key: ep_steps
        name: steps
    - type: MetricByKey
      kwargs:
        key: total_steps
        name: n_env_steps
    - type: CompareValue
      kwargs:
        key: ep_reward
        name: wins
        value: 200
        op: gt  # Greater than
    - type: Timer
  log_keys:
    - rewards_av
    - steps_av
  callbacks:
    - type: SaveBest
      kwargs:
        key: rewards_av
        channel: save_best

# Monitoring
monitoring:
  file_storage:
    path: /home/SoulsAI/saves
    plot:
      xkey: n_env_steps
      ykeys:
        - rewards_av
        - steps_av
        - wins_av
        - time
  grafana: True
  prometheus: True
  wandb:
    project: soulsai_iudex
    entity: amacati
    group: state_obs
    save_dir: /home/SoulsAI/saves

# Client settings
max_episodes: -1  # -1 for infinite runs
enable_interrupt: True
step_delay: 0

watchdog:
  enable: False
  minimum_samples: -1