Automated tutorials push

Author: pytorchbot

_downloads/0c4dc681209d8c964aae9de5e477d280/pendulum.py

@@ -604,7 +604,7 @@ def __init__(self, td_params=None, seed=None, device="cpu"):
     env,
     # ``Unsqueeze`` the observations that we will concatenate
     UnsqueezeTransform(
-        unsqueeze_dim=-1,
+        dim=-1,
         in_keys=["th", "thdot"],
         in_keys_inv=["th", "thdot"],
     ),

_downloads/14b68b9764c79afe8ef88b11fc27bff7/dqn_with_rnn_tutorial.py

@@ -433,7 +433,7 @@
     exploration_module.step(data.numel())
     updater.step()
 
-    with set_exploration_type(ExplorationType.MODE), torch.no_grad():
+    with set_exploration_type(ExplorationType.DETERMINISTIC), torch.no_grad():
         rollout = env.rollout(10000, stoch_policy)
         traj_lens.append(rollout.get(("next", "step_count")).max().item())
 

_downloads/224d2179034ef4c00cd9b86f2976062a/dqn_with_rnn_tutorial.ipynb

@@ -714,7 +714,7 @@
     "    exploration_module.step(data.numel())\n",
     "    updater.step()\n",
     "\n",
-    "    with set_exploration_type(ExplorationType.MODE), torch.no_grad():\n",
+    "    with set_exploration_type(ExplorationType.DETERMINISTIC), torch.no_grad():\n",
     "        rollout = env.rollout(10000, stoch_policy)\n",
     "        traj_lens.append(rollout.get((\"next\", \"step_count\")).max().item())"
    ]

_downloads/4065a985b933a4377d3c7d93557e2282/reinforcement_ppo.ipynb

@@ -635,8 +635,8 @@
     "    in_keys=[\"loc\", \"scale\"],\n",
     "    distribution_class=TanhNormal,\n",
     "    distribution_kwargs={\n",
-    "        \"min\": env.action_spec.space.low,\n",
-    "        \"max\": env.action_spec.space.high,\n",
+    "        \"low\": env.action_spec.space.low,\n",
+    "        \"high\": env.action_spec.space.high,\n",
     "    },\n",
     "    return_log_prob=True,\n",
     "    # we'll need the log-prob for the numerator of the importance weights\n",

_downloads/592c87306513ba042d759e142b59fea4/coding_ddpg.py

@@ -893,7 +893,7 @@ def make_recorder(actor_model_explore, transform_state_dict, record_interval):
         record_frames=1000,
         policy_exploration=actor_model_explore,
         environment=environment,
-        exploration_type=ExplorationType.MEAN,
+        exploration_type=ExplorationType.DETERMINISTIC,
         record_interval=record_interval,
     )
     return recorder_obj

_downloads/7ed508ed54ec36ee5c1d3fa1e8ceede0/reinforcement_ppo.py

@@ -419,8 +419,8 @@
     in_keys=["loc", "scale"],
     distribution_class=TanhNormal,
     distribution_kwargs={
-        "min": env.action_spec.space.low,
-        "max": env.action_spec.space.high,
+        "low": env.action_spec.space.low,
+        "high": env.action_spec.space.high,
     },
     return_log_prob=True,
     # we'll need the log-prob for the numerator of the importance weights

_downloads/8016e5cfa285bd92b9684c45552fffcc/pendulum.ipynb

@@ -769,7 +769,7 @@
     "    env,\n",
     "    # ``Unsqueeze`` the observations that we will concatenate\n",
     "    UnsqueezeTransform(\n",
-    "        unsqueeze_dim=-1,\n",
+    "        dim=-1,\n",
     "        in_keys=[\"th\", \"thdot\"],\n",
     "        in_keys_inv=[\"th\", \"thdot\"],\n",
     "    ),\n",

_downloads/e9ea08c1c8bbc809d69c69a6043d56ee/coding_ddpg.ipynb

@@ -1203,7 +1203,7 @@
     "        record_frames=1000,\n",
     "        policy_exploration=actor_model_explore,\n",
     "        environment=environment,\n",
-    "        exploration_type=ExplorationType.MEAN,\n",
+    "        exploration_type=ExplorationType.DETERMINISTIC,\n",
     "        record_interval=record_interval,\n",
     "    )\n",
     "    return recorder_obj"