Skip to content

Warn when init_noise_std and related params are ignored with tanh_normal (#661) #668

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.

Sign up for GitHub

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

Open
SAY-5 wants to merge 1 commit into
base: main
Choose a base branch
from
+19 −1
Open

Warn when init_noise_std and related params are ignored with tanh_normal (#661) #668

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 19 additions & 1 deletion brax/training/agents/ppo/networks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@

"""PPO networks."""

import warnings
from typing import Any, Literal, Mapping, Sequence, Tuple

from brax.training import distribution
Expand Down Expand Up @@ -116,6 +117,23 @@ def make_ppo_networks(
value_kernel_init_kwargs = value_network_kernel_init_kwargs or {}
mean_kernel_init_kwargs_ = mean_kernel_init_kwargs or {}

if distribution_type == 'tanh_normal':
ignored = []
if init_noise_std != 1.0:
ignored.append(f'init_noise_std={init_noise_std!r}')
if noise_std_type != 'scalar':
ignored.append(f'noise_std_type={noise_std_type!r}')
if state_dependent_std:
ignored.append(f'state_dependent_std={state_dependent_std!r}')
if ignored:
warnings.warn(
f'{", ".join(ignored)} {"has" if len(ignored) == 1 else "have"}'
' no effect with distribution_type="tanh_normal". The standard'
' deviation is determined entirely by the policy network output.'
' These parameters only apply to distribution_type="normal".',
stacklevel=2,
)

parametric_action_distribution: distribution.ParametricDistribution
if distribution_type == 'normal':
parametric_action_distribution = distribution.NormalDistribution(
Expand Down Expand Up @@ -163,4 +181,4 @@ def make_ppo_networks(
policy_network=policy_network,
value_network=value_network,
parametric_action_distribution=parametric_action_distribution,
)
)