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: 251.64 +/- 38.84
|
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 0x7fd05638fb90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd05638fc20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd05638fcb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd05638fd40>", "_build": "<function ActorCriticPolicy._build at 0x7fd05638fdd0>", "forward": "<function ActorCriticPolicy.forward at 0x7fd05638fe60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd05638fef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd05638ff80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd056396050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd0563960e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd056396170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd0563cfe10>"}, "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": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653043157.1865463, "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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "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:c94fc25613bc9cab2220dd98c633babb9ad8abf48cdb5ea69d067489e52eff70
|
3 |
+
size 144130
|
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 0x7fd05638fb90>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd05638fc20>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd05638fcb0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd05638fd40>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fd05638fdd0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fd05638fe60>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd05638fef0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fd05638ff80>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd056396050>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd0563960e0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd056396170>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fd0563cfe10>"
|
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": 1507328,
|
46 |
+
"_total_timesteps": 1500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653043157.1865463,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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": -0.004885333333333408,
|
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": 368,
|
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:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
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:eaca16a8cc6265992085436c16ab1aa908b63cd74a392789cd1e64a2df540590
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f526786d74b5adf26ec124c816153a83f3b459e9fcfff7fe744d87cfe8d90797
|
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:b3c9ca53f3ea9844d6ea74b5a354f97c7c5a07f6cb7ca75d85ffa3415f078e6f
|
3 |
+
size 186457
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 251.636189459122, "std_reward": 38.843322010169516, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-20T11:15:55.299300"}
|