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

remove minibatch_size attribute to SAC trainer #655

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
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
3 changes: 0 additions & 3 deletions reagent/training/dqn_trainer.py
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,6 @@ def __init__(
rl: RLParameters = field(default_factory=RLParameters), # noqa: B008
double_q_learning: bool = True,
bcq: Optional[BCQConfig] = None,
minibatch_size: int = 1024,
minibatches_per_step: int = 1,
optimizer: Optimizer__Union = field( # noqa: B008
default_factory=Optimizer__Union.default
Expand All @@ -62,7 +61,6 @@ def __init__(
rl: RLParameters
double_q_learning: boolean flag to use double-q learning
bcq: a config file for batch-constrained q-learning, defaults to normal
minibatch_size: samples per minibatch
minibatches_per_step: minibatch updates per step
optimizer: q-network optimizer
evaluation: evaluation params, primarily whether to use CPE in eval or not
Expand All @@ -75,7 +73,6 @@ def __init__(
)
assert self._actions is not None, "Discrete-action DQN needs action names"
self.double_q_learning = double_q_learning
self.minibatch_size = minibatch_size
self.minibatches_per_step = minibatches_per_step or 1

self.q_network = q_network
Expand Down
1 change: 0 additions & 1 deletion reagent/training/sac_trainer.py
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,6 @@ def __init__(
alpha_optimizer: Optional[Optimizer__Union] = field( # noqa: B008
default_factory=Optimizer__Union.default
),
minibatch_size: int = 1024,
entropy_temperature: float = 0.01,
logged_action_uniform_prior: bool = True,
target_entropy: float = -1.0,
Expand Down