rl_config.json

{
    "train_path": "../data/norm-multi-woz/train_dials.json",
    "valid_path": "../data/norm-multi-woz/val_dials.json",
    "test_path": "../data/norm-multi-woz/test_dials.json",
    "sv_config_path": "sys_config_log_model/2020-05-12-14-51-49-actz_cat/config.json",
    "sv_model_path": "sys_config_log_model/2020-05-12-14-51-49-actz_cat/19-model",
    "rl_config_path": "sys_config_log_model/2020-05-12-14-51-49-actz_cat/rl-2020-05-18-10-50-48/rl_config.json",
    "rl_model_path": "sys_config_log_model/2020-05-12-14-51-49-actz_cat/rl-2020-05-18-10-50-48/rl_model",
    "ppl_best_model_path": "sys_config_log_model/2020-05-12-14-51-49-actz_cat/rl-2020-05-18-10-50-48/ppl_best.model",
    "reward_best_model_path": "sys_config_log_model/2020-05-12-14-51-49-actz_cat/rl-2020-05-18-10-50-48/reward_best.model",
    "record_path": "sys_config_log_model/2020-05-12-14-51-49-actz_cat/rl-2020-05-18-10-50-48",
    "record_freq": 200,
    "sv_train_freq": 0,
    "use_gpu": true,
    "nepoch": 10,
    "nepisode": 0,
    "tune_pi_only": false,
    "max_words": 100,
    "temperature": 1.0,
    "episode_repeat": 1.0,
    "rl_lr": 0.01,
    "momentum": 0.0,
    "nesterov": false,
    "gamma": 0.99,
    "rl_clip": 5.0,
    "random_seed": 38
}