Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Hyperparam tunning - few epochs, high vf coeff (c1) - medium entropy coeff (c2) #64

Open
wants to merge 1 commit into
base: ppo-hyperparam-tuning
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions main.py
Original file line number Diff line number Diff line change
Expand Up @@ -46,8 +46,8 @@ def train(config):
'mini_batch_size': 128,
'memory_size': 2000,
'eps': 0.2,
'c1': tune.quniform(0.5, 2.5, 0.25), # Value Function coeff
'c2': tune.quniform(0.00, 0.16, 0.02), # Entropy coeff
'c1': tune.quniform(1.5, 2.5, 0.5), # Value Function coeff
'c2': tune.quniform(0.00, 0.06, 0.02), # Entropy coeff
'lr': 1e-3, # Learning rate
'gamma': 0.99, # Discount rate
'log_interval': 10, # controls how often we log progress
Expand All @@ -56,14 +56,14 @@ def train(config):
'experiment': experiment,
'action_set_num': 4,
'train': True,
'seed': tune.grid_search([7081960, 1000, 190421])
'seed': 190421
}

analysis = tune.run(
train,
metric='running_reward',
mode='max',
num_samples=18,
num_samples=3,
resources_per_trial={"cpu": 0.4, "gpu": 0.3},
config=hyperparams,
)
Expand Down