# MuZero-style AGI Jobs demo configuration
owner:
  pause_planning: false
  max_capital_per_action: 2500.0
  governance_contact: "owner@agijobs.example"

experiment:
  seed: 17
  device: "cpu"
  episodes: 48
  evaluation_episodes: 64
  artifact_dir: "demo/MuZero-style-v0/artifacts"

environment:
  episode_length: 6
  job_pool_size: 5
  success_noise: 0.08
  discount: 0.997
  max_budget: 10000.0
  stochastic_fail_penalty: 0.2

network:
  observation_dim: 27
  hidden_dim: 64
  latent_dim: 48
  reward_support: [-4, 4]
  value_support: [-20, 20]
  policy_temperature: 1.0

planner:
  enable_muzero_planning: true
  default_simulations: 96
  max_simulations: 256
  exploration_constant: 1.5
  dirichlet_alpha: 0.3
  dirichlet_epsilon: 0.25
  temperature: 1.0
  visit_temperature_schedule:
    warmup_episode: 24
    min_temperature: 0.05

thermostat:
  enable: true
  low_entropy_threshold: 0.25
  high_entropy_threshold: 0.65
  min_simulations: 32
  max_simulations: 192
  latency_budget_ms: 140
  simulation_cost_ms: 1.1

sentinel:
  enable: true
  value_error_alpha: 0.1
  value_error_threshold: 0.9
  drift_window: 12
  fallback_on_violation: true

training:
  batch_size: 32
  unroll_steps: 5
  td_steps: 5
  learning_rate: 0.0008
  weight_decay: 0.000001
  replay_capacity: 2048
  warmup_steps: 32
  reanalyse_ratio: 0.25
  value_loss_weight: 0.9
  reward_loss_weight: 1.0
  policy_loss_weight: 1.0
  checkpoint_interval: 16

telemetry:
  enable: true
  flush_interval: 5
  prometheus_format: false
  sample_rate: 1.0

baselines:
  greedy_immediacy_bias: 0.05
  policy_temperature: 0.7