Fix formatting in 7_train_density.ipynb and density.rst

HumanCompatibleAI · Sep 6, 2023 · 2dcc6cd · 2dcc6cd
1 parent 5449404
commit 2dcc6cd
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 15 deletions.
diff --git a/docs/algorithms/density.rst b/docs/algorithms/density.rst
@@ -44,12 +44,7 @@ Detailed example notebook: :doc:`../tutorials/7_train_density`
     rollouts = serialize.load("../tests/testdata/expert_models/pendulum_0/rollouts/final.npz")
 
     imitation_trainer = PPO(
-        ActorCriticPolicy,
-        env,
-        learning_rate=3e-4,
-        gamma=0.95,
-        ent_coef=1e-4,
-        n_steps=2048
+        ActorCriticPolicy, env, learning_rate=3e-4, gamma=0.95, ent_coef=1e-4, n_steps=2048
     )
     density_trainer = db.DensityAlgorithm(
         venv=env,

diff --git a/docs/tutorials/7_train_density.ipynb b/docs/tutorials/7_train_density.ipynb
@@ -87,12 +87,7 @@
     "\n",
     "\n",
     "imitation_trainer = PPO(\n",
-    "    ActorCriticPolicy, \n",
-    "    env, \n",
-    "    learning_rate=3e-4,\n",
-    "    gamma=0.95,\n",
-    "    ent_coef=1e-4,\n",
-    "    n_steps=2048\n",
+    "    ActorCriticPolicy, env, learning_rate=3e-4, gamma=0.95, ent_coef=1e-4, n_steps=2048\n",
     ")\n",
     "density_trainer = db.DensityAlgorithm(\n",
     "    venv=env,\n",
@@ -115,9 +110,7 @@
    "outputs": [],
    "source": [
     "# evaluate the expert\n",
-    "expert_rewards, _ = evaluate_policy(\n",
-    "    expert, env, 100, return_episode_rewards=True\n",
-    ")\n",
+    "expert_rewards, _ = evaluate_policy(expert, env, 100, return_episode_rewards=True)\n",
     "\n",
     "# evaluate the learner before training\n",
     "learner_rewards_before_training, _ = evaluate_policy(\n",