Meta

Meta()

---

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:

.fields

.fields(
   cls, predicate = lambdax: True
)

---

Remember the transaction.

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

Arguments

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

.constraints

.constraints(
   cls, predicate = lambdax: True
)

---

Remember the transaction.

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

Arguments

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

.indexes

.indexes(
   cls, predicate = lambdax: True
)

---

Remember the transaction.

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

Arguments

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

.query

.query(
   cls
)

---

Remember the transaction.

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

Arguments

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

---

normalize_kwargs

.normalize_kwargs(
   meta, **kwargs
)

---

Remember the transaction.

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

Arguments

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