Arrow

Arrow()

---

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.

---

ChessEnv

---

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:

.copy

.copy(
   *, stack = True
)

---

Remember the transaction.

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

Arguments

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

.reset

.reset()

---

Remember the transaction.

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

Arguments

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

.get_observation

.get_observation(
   orientation = WHITE, flipped = False, mode = 'str'
)

---

Remember the transaction.

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

Arguments

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

.get_reward

.get_reward(
   piece
)

---

Remember the transaction.

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

Arguments

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

.step

.step(
   move, move_type = 'uci'
)

---

Remember the transaction.

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

Arguments

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

.result

.result(
   *, claim_draw = False
)

---

Remember the transaction.

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

Arguments

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

.unicode

.unicode(
   *, invert_color = False, borders = False, empty_square = 'â\xad˜'
)

---

Remember the transaction.

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

Arguments

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

.render

.render(
   *, orientation = WHITE, flipped = False, mode = 'str'
)

---

Remember the transaction.

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

Arguments

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

---

arrow

.arrow(
   screen, color, start, end, thickness
)

---

Remember the transaction.

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

Arguments

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

---

create_move_labels

.create_move_labels()

---

Remember the transaction.

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

Arguments

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