training_config:
  rl_framework: SB3
  rl_algorithm: PPO
  seed: 333
  n_learn_episodes: 1
  n_eval_episodes: 5
  max_steps_per_episode: 128
  deterministic_eval: false
  n_agents: 1
  agent_references:
    - defender

io_settings:
  save_checkpoints: true
  checkpoint_interval: 5
  save_step_metadata: false
  save_pcap_logs: true
  save_sys_logs: true


game:
  max_episode_length: 256
  ports:
    - ARP
    - DNS
    - HTTP
    - POSTGRES_SERVER
  protocols:
    - ICMP
    - TCP
    - UDP