mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-09 22:10:56 +08:00
Add config file in trade
Update readme in trade Update highfreq to delete nan order
This commit is contained in:
Mingzhe Han
76
examples/trade/exp/example/OPD/config.yml
Normal file
76
examples/trade/exp/example/OPD/config.yml
Normal file
@@ -0,0 +1,76 @@
|
||||
seed: 42
|
||||
task: train
|
||||
log_dir: example/OPD
|
||||
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
|
||||
- name: teacher_action
|
||||
type: interval
|
||||
size: 1
|
||||
loc: ../data/feature/teacher/
|
||||
obs:
|
||||
name: RuleTeacher
|
||||
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_sup
|
||||
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
|
||||
sup_coef: 0.01
|
||||
network_conf:
|
||||
name: OPD
|
||||
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.
|
||||
71
examples/trade/exp/example/OPDS/config.yml
Normal file
71
examples/trade/exp/example/OPDS/config.yml
Normal file
@@ -0,0 +1,71 @@
|
||||
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.
|
||||
71
examples/trade/exp/example/OPDT/config.yml
Normal file
71
examples/trade/exp/example/OPDT/config.yml
Normal file
@@ -0,0 +1,71 @@
|
||||
seed: 42
|
||||
task: train
|
||||
log_dir: example/OPDT
|
||||
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: Teacher
|
||||
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.
|
||||
76
examples/trade/exp/example/OPDT_b/config.yml
Normal file
76
examples/trade/exp/example/OPDT_b/config.yml
Normal file
@@ -0,0 +1,76 @@
|
||||
seed: 42
|
||||
task: eval
|
||||
log_dir: example/OPDT_b
|
||||
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/all/
|
||||
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_path: policy_best
|
||||
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: Teacher
|
||||
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.
|
||||
search:
|
||||
optim.weight_decay:
|
||||
type: choice
|
||||
value: [0.]
|
||||
70
examples/trade/exp/example/PPO/config.yml
Normal file
70
examples/trade/exp/example/PPO/config.yml
Normal file
@@ -0,0 +1,70 @@
|
||||
seed: 42
|
||||
task: train
|
||||
log_dir: example/PPO
|
||||
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:
|
||||
PPO_Reward:
|
||||
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.
|
||||
Reference in New Issue
Block a user