Skip to content

Commit b2fab67

Browse files
boris-il-forteboris-il-forte
committed
Fixed textual output of example scripts
1 parent de6f703 commit b2fab67

File tree

7 files changed

+14
-14
lines changed

7 files changed

+14
-14
lines changed

‎examples/habitat/habitat_rearrange_sac.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -150,7 +150,7 @@ def experiment(alg, n_epochs, n_steps, n_episodes_test):
150150

151151
J = np.mean(dataset.discounted_return)
152152
R = np.mean(dataset.undiscounted_return)
153-
E = agent.policy.entropy(dataset.state)
153+
E = agent.policy.entropy(dataset.state).item()
154154

155155
logger.epoch_info(0, J=J, R=R, entropy=E)
156156

@@ -162,7 +162,7 @@ def experiment(alg, n_epochs, n_steps, n_episodes_test):
162162

163163
J = np.mean(dataset.discounted_return)
164164
R = np.mean(dataset.undiscounted_return)
165-
E = agent.policy.entropy(dataset.state)
165+
E = agent.policy.entropy(dataset.state).item()
166166

167167
logger.epoch_info(n+1, J=J, R=R, entropy=E)
168168

‎examples/isaac_example.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -81,7 +81,7 @@ def experiment(cfg_dict, headless, alg, n_epochs, n_steps, n_steps_per_fit, n_ep
8181

8282
J = torch.mean(dataset.discounted_return)
8383
R = torch.mean(dataset.undiscounted_return)
84-
E = agent.policy.entropy()
84+
E = agent.policy.entropy().item()
8585

8686
logger.epoch_info(0, J=J, R=R, entropy=E)
8787

@@ -91,7 +91,7 @@ def experiment(cfg_dict, headless, alg, n_epochs, n_steps, n_steps_per_fit, n_ep
9191

9292
J = torch.mean(dataset.discounted_return)
9393
R = torch.mean(dataset.undiscounted_return)
94-
E = agent.policy.entropy()
94+
E = agent.policy.entropy().item()
9595

9696
logger.epoch_info(it+1, J=J, R=R, entropy=E)
9797

‎examples/mujoco_locomotion_ppo.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -97,7 +97,7 @@ def experiment(env, n_epochs, n_steps, n_episodes_test):
9797

9898
J = np.mean(dataset.discounted_return)
9999
R = np.mean(dataset.undiscounted_return)
100-
E = agent.policy.entropy()
100+
E = agent.policy.entropy().item()
101101

102102
logger.epoch_info(0, J=J, R=R, entropy=E)
103103

@@ -107,7 +107,7 @@ def experiment(env, n_epochs, n_steps, n_episodes_test):
107107

108108
J = np.mean(dataset.discounted_return)
109109
R = np.mean(dataset.undiscounted_return)
110-
E = agent.policy.entropy()
110+
E = agent.policy.entropy().item()
111111

112112
logger.epoch_info(it + 1, J=J, R=R, entropy=E)
113113

‎examples/pendulum_a2c.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@ def experiment(alg, env_id, horizon, gamma, n_epochs, n_steps, n_steps_per_fit,
7373

7474
J = np.mean(dataset.discounted_return)
7575
R = np.mean(dataset.undiscounted_return)
76-
E = agent.policy.entropy()
76+
E = agent.policy.entropy().item()
7777

7878
logger.epoch_info(0, J=J, R=R, entropy=E)
7979

@@ -83,7 +83,7 @@ def experiment(alg, env_id, horizon, gamma, n_epochs, n_steps, n_steps_per_fit,
8383

8484
J = np.mean(dataset.discounted_return)
8585
R = np.mean(dataset.undiscounted_return)
86-
E = agent.policy.entropy()
86+
E = agent.policy.entropy().item()
8787

8888
logger.epoch_info(it+1, J=J, R=R, entropy=E)
8989

‎examples/pendulum_sac.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -127,7 +127,7 @@ def experiment(alg, n_epochs, n_steps, n_steps_test, save, load):
127127

128128
J = np.mean(dataset.discounted_return)
129129
R = np.mean(dataset.undiscounted_return)
130-
E = agent.policy.entropy(dataset.state)
130+
E = agent.policy.entropy(dataset.state).item()
131131

132132
logger.epoch_info(0, J=J, R=R, entropy=E)
133133

@@ -139,7 +139,7 @@ def experiment(alg, n_epochs, n_steps, n_steps_test, save, load):
139139

140140
J = np.mean(dataset.discounted_return)
141141
R = np.mean(dataset.undiscounted_return)
142-
E = agent.policy.entropy(dataset.state)
142+
E = agent.policy.entropy(dataset.state).item()
143143

144144
logger.epoch_info(n+1, J=J, R=R, entropy=E)
145145

‎examples/pendulum_trust_region.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -70,7 +70,7 @@ def experiment(alg, env_id, horizon, gamma, n_epochs, n_steps, n_steps_per_fit,
7070

7171
J = np.mean(dataset.discounted_return)
7272
R = np.mean(dataset.undiscounted_return)
73-
E = agent.policy.entropy()
73+
E = agent.policy.entropy().item()
7474

7575
logger.epoch_info(0, J=J, R=R, entropy=E)
7676

@@ -80,7 +80,7 @@ def experiment(alg, env_id, horizon, gamma, n_epochs, n_steps, n_steps_per_fit,
8080

8181
J = np.mean(dataset.discounted_return)
8282
R = np.mean(dataset.undiscounted_return)
83-
E = agent.policy.entropy()
83+
E = agent.policy.entropy().item()
8484

8585
logger.epoch_info(it+1, J=J, R=R, entropy=E)
8686

‎examples/vectorized_core/pendulum_trust_region.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@ def experiment(alg, env_id, horizon, gamma, n_epochs, n_steps, n_steps_per_fit,
7373

7474
J = np.mean(dataset.discounted_return)
7575
R = np.mean(dataset.undiscounted_return)
76-
E = agent.policy.entropy()
76+
E = agent.policy.entropy().item()
7777

7878
logger.epoch_info(0, J=J, R=R, entropy=E)
7979

@@ -83,7 +83,7 @@ def experiment(alg, env_id, horizon, gamma, n_epochs, n_steps, n_steps_per_fit,
8383

8484
J = np.mean(dataset.discounted_return)
8585
R = np.mean(dataset.undiscounted_return)
86-
E = agent.policy.entropy()
86+
E = agent.policy.entropy().item()
8787

8888
logger.epoch_info(it+1, J=J, R=R, entropy=E)
8989

0 commit comments

Comments
 (0)