BatchNorm

BatchNorm(
   features, eps: float = 1e-05, momentum: float = 0.1, affine: bool = True,
   track_running_stats: bool = True
)

---

Deep Deterministic Policy Gradient

Arguments

actor_model (keras.nn.Model instance): See Model for details. critic_model (keras.nn.Model instance): See Model for details. optimizer (keras.optimizers.Optimizer instance): See Optimizer for details. action_inp (keras.layers.Input / keras.layers.InputLayer instance): See Input for details. tau (float): tau. gamma (float): gamma.

Methods:

.reset_running_stats

.reset_running_stats()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

.reset_parameters

.reset_parameters()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

.forward

.forward(
   inp
)

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.