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

adds some descriptions to parseargs arguments #319

Merged
merged 3 commits into from
Oct 12, 2018
Merged
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
40 changes: 27 additions & 13 deletions examples/ale/train_dqn_ale.py
Original file line number Diff line number Diff line change
Expand Up @@ -78,31 +78,45 @@ def parse_agent(agent):

def main():
parser = argparse.ArgumentParser()
parser.add_argument('--env', type=str, default='BreakoutNoFrameskip-v4')
parser.add_argument('--env', type=str, default='BreakoutNoFrameskip-v4',
help='OpenAI Atari domain to perform algorithm on.')
parser.add_argument('--outdir', type=str, default='results',
help='Directory path to save output files.'
' If it does not exist, it will be created.')
parser.add_argument('--seed', type=int, default=0,
help='Random seed [0, 2 ** 31)')
parser.add_argument('--gpu', type=int, default=0)
parser.add_argument('--gpu', type=int, default=0,
help='GPU to use, set to -1 if no GPU.')
parser.add_argument('--demo', action='store_true', default=False)
parser.add_argument('--load', type=str, default=None)
parser.add_argument('--final-exploration-frames',
type=int, default=10 ** 6)
parser.add_argument('--final-epsilon', type=float, default=0.01)
parser.add_argument('--eval-epsilon', type=float, default=0.001)
type=int, default=10 ** 6,
help='Timesteps after which we stop ' +
'annealing exploration rate')
parser.add_argument('--final-epsilon', type=float, default=0.01,
help='Final value of epsilon during training.')
parser.add_argument('--eval-epsilon', type=float, default=0.001,
help='Exploration epsilon used during eval episodes.')
parser.add_argument('--noisy-net-sigma', type=float, default=None)
parser.add_argument('--arch', type=str, default='doubledqn',
choices=['nature', 'nips', 'dueling', 'doubledqn'])
parser.add_argument('--steps', type=int, default=5 * 10 ** 7)
choices=['nature', 'nips', 'dueling', 'doubledqn'],
help='Network architecture to use.')
parser.add_argument('--steps', type=int, default=5 * 10 ** 7,
help='Total number of timesteps to train the agent.')
parser.add_argument('--max-episode-len', type=int,
default=30 * 60 * 60 // 4, # 30 minutes with 60/4 fps
help='Maximum number of steps for each episode.')
parser.add_argument('--replay-start-size', type=int, default=5 * 10 ** 4)
help='Maximum number of timesteps for each episode.')
parser.add_argument('--replay-start-size', type=int, default=5 * 10 ** 4,
help='Minimum replay buffer size before ' +
'performing gradient updates.')
parser.add_argument('--target-update-interval',
type=int, default=3 * 10 ** 4)
parser.add_argument('--eval-interval', type=int, default=10 ** 5)
parser.add_argument('--update-interval', type=int, default=4)
type=int, default=3 * 10 ** 4,
help='Frequency (in timesteps) at which ' +
'the target network is updated.')
parser.add_argument('--eval-interval', type=int, default=10 ** 5,
help='Frequency (in timesteps) of evaluation phase.')
parser.add_argument('--update-interval', type=int, default=4,
help='Frequency (in timesteps) of network updates.')
parser.add_argument('--eval-n-runs', type=int, default=10)
parser.add_argument('--no-clip-delta',
dest='clip_delta', action='store_false')
Expand All @@ -117,7 +131,7 @@ def main():
help='Monitor env. Videos and additional information'
' are saved as output files.')
parser.add_argument('--lr', type=float, default=2.5e-4,
help='Learning rate')
help='Learning rate.')
parser.add_argument('--prioritized', action='store_true', default=False,
help='Use prioritized experience replay.')
args = parser.parse_args()
Expand Down