First cut LunarLander with ppo from stable-baselines3
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: 216.03 +/- 55.34
|
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 0x7f9c5373b5f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9c5373b680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9c5373b710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9c5373b7a0>", "_build": "<function ActorCriticPolicy._build at 0x7f9c5373b830>", "forward": "<function ActorCriticPolicy.forward at 0x7f9c5373b8c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9c5373b950>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9c5373b9e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9c5373ba70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9c5373bb00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9c5373bb90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f9c53761150>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1656024824.116909, "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": 248, "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:caf10ecd671b858f105c2fcd3d99bd5ff7e2ad98114955fab0a8c885d4f296d7
|
3 |
+
size 144145
|
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 0x7f9c5373b5f0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9c5373b680>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9c5373b710>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9c5373b7a0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9c5373b830>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9c5373b8c0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9c5373b950>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9c5373b9e0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9c5373ba70>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9c5373bb00>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9c5373bb90>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f9c53761150>"
|
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": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1656024824.116909,
|
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": -0.015808000000000044,
|
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": 248,
|
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:b5ae0812df050c057fefb4098a802eeacf15726cdc851826b8620417752ba5f7
|
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:cd8f5cef58bc5dd2aca97aa43b1e67cb0ff07c54ee8d9b3774b8b40016f157e2
|
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:d1f83115d020ea68e2bb2d1ba74d4435e1fab4327880fb0ceedc3cd0efa56b09
|
3 |
+
size 216651
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 216.02963383130987, "std_reward": 55.33812785435589, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-23T23:31:21.938465"}
|