mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
42 lines
1.2 KiB
YAML
42 lines
1.2 KiB
YAML
cartpole_crr:
|
|
env: 'CartPole-v0'
|
|
run: CRR
|
|
stop:
|
|
evaluation/episode_reward_mean: 200
|
|
training_iteration: 100
|
|
config:
|
|
input: 'dataset'
|
|
input_config:
|
|
paths: 'tests/data/cartpole/large.json'
|
|
format: 'json'
|
|
framework: torch
|
|
num_workers: 3
|
|
gamma: 0.99
|
|
train_batch_size: 2048
|
|
critic_hidden_activation: 'tanh'
|
|
critic_hiddens: [128, 128, 128]
|
|
critic_lr: 0.0003
|
|
actor_hidden_activation: 'tanh'
|
|
actor_hiddens: [128, 128, 128]
|
|
actor_lr: 0.0003
|
|
actions_in_input_normalized: True
|
|
clip_actions: True
|
|
# Q function update setting
|
|
twin_q: True
|
|
target_network_update_freq: 1
|
|
tau: 0.0005
|
|
# evaluation
|
|
evaluation_config:
|
|
explore: False
|
|
input: sampler
|
|
evaluation_duration: 10
|
|
evaluation_duration_unit: episodes
|
|
evaluation_interval: 1
|
|
evaluation_num_workers: 1
|
|
evaluation_parallel_to_training: True
|
|
# specific to CRR
|
|
temperature: 1.0
|
|
weight_type: bin
|
|
advantage_type: expectation
|
|
max_weight: 20.0
|
|
n_action_sample: 4
|