kengz/SLM-Lab

{
  "async_sac_lunar": {
    "agent": [{
      "name": "SoftActorCritic",
      "algorithm": {
        "name": "SoftActorCritic",
        "action_pdtype": "GumbelSoftmax",
        "action_policy": "default",
        "gamma": 0.99,
        "training_frequency": 1
      },
      "memory": {
        "name": "Replay",
        "batch_size": 256,
        "max_size": 200000,
        "use_cer": true
      },
      "net": {
        "type": "MLPNet",
        "hid_layers": [64, 64, 32],
        "hid_layers_activation": "relu",
        "init_fn": "orthogonal_",
        "clip_grad_val": 0.5,
        "loss_spec": {
          "name": "MSELoss"
        },
        "optim_spec": {
          "name": "GlobalAdam",
          "lr": 1e-3,
        },
        "lr_scheduler_spec": null,
        "update_type": "polyak",
        "update_frequency": 1,
        "polyak_coef": 0.005,
        "gpu": false
      }
    }],
    "env": [{
      "name": "LunarLander-v2",
      "frame_op": "concat",
      "frame_op_len": 4,
      "max_t": null,
      "max_frame": 8e5,
      "num_envs": 8,
      "normalize_state": false
    }],
    "body": {
      "product": "outer",
      "num": 1
    },
    "meta": {
      "distributed": "shared",
      "log_frequency": 500,
      "eval_frequency": 500,
      "rigorous_eval": 0,
      "max_session": 6,
      "max_trial": 1,
    },
    "search": {
      "env": [{
        "num_envs__grid_search": [4, 6, 8, 10]
      }],
      "meta": {
        "max_session__grid_search": [4, 6, 8, 10]
      }
    }
  }
}