Study Log (2021.10)

less than 1 minute read

2021-10-01

  • S-K RL
    • train_FT10_ppo_node_only.py
      • do_simulate_on_aggregated_state()
      • value_loss, action_loss, dist_entropy = agent.fit(eval=0, reward_setting=’utilization’, device=device, return_scaled=False)
      • eval_performance = evaluate_agent_on_aggregated_state(simulator=sim, agent=agent, device=’cpu’, mode=’node_mode’)
      • val_performance = validation(agent, path, mode=’node_mode’)
    • pyjssp 버전 구분
      • GNN-MARL Lastest용
      • GNN-MARL Stable용

Template

Updated:

Comments