Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 178.82 +/- 14.19
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f1cd6684d40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1cd6684dd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1cd6684e60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1cd6684ef0>", "_build": "<function ActorCriticPolicy._build at 0x7f1cd6684f80>", "forward": "<function ActorCriticPolicy.forward at 0x7f1cd668b050>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1cd668b0e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f1cd668b170>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1cd668b200>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1cd668b290>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1cd668b320>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f1cd665c4b0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653486925.0234387, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d945c13ae6658c987105eb2d0b384899eb0a98c630655e5beb5106368515fb10
|
3 |
+
size 144152
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
+
"__module__": "stable_baselines3.common.policies",
|
6 |
+
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f1cd6684d40>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1cd6684dd0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1cd6684e60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1cd6684ef0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f1cd6684f80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f1cd668b050>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1cd668b0e0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f1cd668b170>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1cd668b200>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1cd668b290>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1cd668b320>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f1cd665c4b0>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653486925.0234387,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 124,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2bd21109ec4b6d8fb6b87c1e3454aacc34fae6e77d998540b4a179286b834d6
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47134d9013791caa2bde43c63a6fbf24b2ac077312e16d43107dbc87d88ad448
|
3 |
+
size 43201
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb16423265e5fb068f496ecd41dde42b5eebd3e4017f05dffe164abfb3c447dd
|
3 |
+
size 260133
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 178.81539304320108, "std_reward": 14.18847271646649, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-25T14:08:10.887751"}
|