seed: 42
task: train
log_dir: example/OPDS
buffer_size: 80000
io_conf:
  test_sampler: TestSampler
  train_sampler: Sampler
  test_logger: DFLogger
resources:
  num_cpus: 24
  num_gpus: 1
  device: cuda
train_paths:
  raw_dir: ../data/backtest/
  order_dir: ../data/order/train/
valid_paths:
  raw_dir: ../data/backtest/
  order_dir: ../data/order/valid/
test_paths:
  raw_dir: ../data/backtest/
  order_dir: ../data/order/test/
env_conf:
  name: StockEnv_Acc
  max_step_num: 237
  limit: 10
  time_interval: 30
  interval_num: 8
  features:
  - name: raw
    type: range
    loc: ../data/normed_feature/
    size: 180
  obs:
    name: TeacherObs
    config: {}
  action:
    name: Static_Action
    config:
      action_num: 5
      action_map: [0, 0.25, 0.5, 0.75, 1]
  reward:
    VP_Penalty_small_vec:
      penalty: 100
      coefficient: 1
policy_conf:
  name: PPO
  config:
    discount_factor: 1.
    max_grad_norm: 100.
    reward_normalization: False
    eps_clip: 0.3
    value_clip: True
    vf_coef: 1.
    gae_lambda: 1.
    vf_clip_para: 0.3
network_conf:
  name: PPO
  config:
    hidden_size: 64
    out_shape: 5
    fc_size: 32
    cnn_shape: [30, 6]
optim:
  lr: 1e-4
  batch_size: 1024
  max_epoch: 30
  step_per_epoch: 20
  collect_per_step: 10000
  repeat_per_collect: 5
  early_stopping: 5
  weight_decay: 0.