init commit
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-mlppolicy-LunarLander-v2.zip +3 -0
- ppo-mlppolicy-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-mlppolicy-LunarLander-v2/data +94 -0
- ppo-mlppolicy-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-mlppolicy-LunarLander-v2/policy.pth +3 -0
- ppo-mlppolicy-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-mlppolicy-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: 0.39 +/- 42.53
|
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 0x7f3b8e6cb170>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3b8e6cb200>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3b8e6cb290>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3b8e6cb320>", "_build": "<function ActorCriticPolicy._build at 0x7f3b8e6cb3b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3b8e6cb440>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3b8e6cb4d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3b8e6cb560>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3b8e6cb5f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3b8e6cb680>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3b8e6cb710>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3b8e7220f0>"}, "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": 1656260109.5200353, "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:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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-mlppolicy-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c5db441d5dc070ed20bc16809eec31d6c3e32706df6f1e3bf0c20fe839e956c
|
3 |
+
size 144132
|
ppo-mlppolicy-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-mlppolicy-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 0x7f3b8e6cb170>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3b8e6cb200>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3b8e6cb290>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3b8e6cb320>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3b8e6cb3b0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3b8e6cb440>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3b8e6cb4d0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3b8e6cb560>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3b8e6cb5f0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3b8e6cb680>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3b8e6cb710>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f3b8e7220f0>"
|
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": 1656260109.5200353,
|
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": 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-mlppolicy-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcc5dc9b81e13e99a246d8ee59ba84f43df4a9e7f930d455c71c9a9e770816aa
|
3 |
+
size 84829
|
ppo-mlppolicy-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:620da297a6a30f29c217116210e0c6a22f6e48a5da2af2e341f2821cdb17849e
|
3 |
+
size 43201
|
ppo-mlppolicy-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-mlppolicy-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 sha256:74df83b249edd5df03af4f8182a8d40ccca5a87b64f3aef38bd56aa85e2a6aaf
|
3 |
+
size 259329
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 0.3873426948557608, "std_reward": 42.53457309329353, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-26T16:39:07.918454"}
|