Upload PPO MountainCar-v0 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- ppo-mountaincar-v0.zip +3 -0
- ppo-mountaincar-v0/_stable_baselines3_version +1 -0
- ppo-mountaincar-v0/data +97 -0
- ppo-mountaincar-v0/policy.optimizer.pth +3 -0
- ppo-mountaincar-v0/policy.pth +3 -0
- ppo-mountaincar-v0/pytorch_variables.pth +3 -0
- ppo-mountaincar-v0/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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- MountainCar-v0
|
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: -89.20 +/- 6.54
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: MountainCar-v0
|
20 |
+
type: MountainCar-v0
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **MountainCar-v0**
|
24 |
+
This is a trained model of a **PPO** agent playing **MountainCar-v0** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7ff2d97d29e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff2d97d2a70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff2d97d2b00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff2d97d2b90>", "_build": "<function ActorCriticPolicy._build at 0x7ff2d97d2c20>", "forward": "<function ActorCriticPolicy.forward at 0x7ff2d97d2cb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff2d97d2d40>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff2d97d2dd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff2d97d2e60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff2d97d2ef0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff2d97d2f80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff2d981da20>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVaQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoC0sChZSMAUOUdJRSlIwEaGlnaJRoEyiWCAAAAAAAAACamRk/KVyPPZRoC0sChZRoFnSUUpSMDWJvdW5kZWRfYmVsb3eUaBMolgIAAAAAAAAAAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBZ0lFKUjA1ib3VuZGVkX2Fib3ZllGgTKJYCAAAAAAAAAAEBlGgiSwKFlGgWdJRSlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "_shape": [2], "low": "[-1.2 -0.07]", "high": "[0.6 0.07]", "bounded_below": "[ True True]", "bounded_above": "[ True True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 3, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 10500, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652359951.350326, "learning_rate": {":type:": "<class 'function'>", ":serialized:": "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"}, "tensorboard_log": "logs", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAOU1S7+LmMW8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.98976, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 9820, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-mountaincar-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2f74847d6cd4366f4f6ec876719fde433fbb7f874f61bd0cb85136ade41af99
|
3 |
+
size 132868
|
ppo-mountaincar-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-mountaincar-v0/data
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7ff2d97d29e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff2d97d2a70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff2d97d2b00>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff2d97d2b90>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff2d97d2c20>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff2d97d2cb0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff2d97d2d40>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff2d97d2dd0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff2d97d2e60>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff2d97d2ef0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff2d97d2f80>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7ff2d981da20>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gAWVaQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoC0sChZSMAUOUdJRSlIwEaGlnaJRoEyiWCAAAAAAAAACamRk/KVyPPZRoC0sChZRoFnSUUpSMDWJvdW5kZWRfYmVsb3eUaBMolgIAAAAAAAAAAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBZ0lFKUjA1ib3VuZGVkX2Fib3ZllGgTKJYCAAAAAAAAAAEBlGgiSwKFlGgWdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
2
|
29 |
+
],
|
30 |
+
"low": "[-1.2 -0.07]",
|
31 |
+
"high": "[0.6 0.07]",
|
32 |
+
"bounded_below": "[ True True]",
|
33 |
+
"bounded_above": "[ True True]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 3,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 1,
|
45 |
+
"num_timesteps": 10500,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1652359951.350326,
|
51 |
+
"learning_rate": {
|
52 |
+
":type:": "<class 'function'>",
|
53 |
+
":serialized:": "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"
|
54 |
+
},
|
55 |
+
"tensorboard_log": "logs",
|
56 |
+
"lr_schedule": {
|
57 |
+
":type:": "<class 'function'>",
|
58 |
+
":serialized:": "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"
|
59 |
+
},
|
60 |
+
"_last_obs": {
|
61 |
+
":type:": "<class 'numpy.ndarray'>",
|
62 |
+
":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAOU1S7+LmMW8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="
|
63 |
+
},
|
64 |
+
"_last_episode_starts": {
|
65 |
+
":type:": "<class 'numpy.ndarray'>",
|
66 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
67 |
+
},
|
68 |
+
"_last_original_obs": null,
|
69 |
+
"_episode_num": 0,
|
70 |
+
"use_sde": false,
|
71 |
+
"sde_sample_freq": -1,
|
72 |
+
"_current_progress_remaining": 0.98976,
|
73 |
+
"ep_info_buffer": {
|
74 |
+
":type:": "<class 'collections.deque'>",
|
75 |
+
":serialized:": "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"
|
76 |
+
},
|
77 |
+
"ep_success_buffer": {
|
78 |
+
":type:": "<class 'collections.deque'>",
|
79 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
80 |
+
},
|
81 |
+
"_n_updates": 9820,
|
82 |
+
"n_steps": 2048,
|
83 |
+
"gamma": 0.99,
|
84 |
+
"gae_lambda": 0.95,
|
85 |
+
"ent_coef": 0.0,
|
86 |
+
"vf_coef": 0.5,
|
87 |
+
"max_grad_norm": 0.5,
|
88 |
+
"batch_size": 64,
|
89 |
+
"n_epochs": 10,
|
90 |
+
"clip_range": {
|
91 |
+
":type:": "<class 'function'>",
|
92 |
+
":serialized:": "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"
|
93 |
+
},
|
94 |
+
"clip_range_vf": null,
|
95 |
+
"normalize_advantage": true,
|
96 |
+
"target_kl": null
|
97 |
+
}
|
ppo-mountaincar-v0/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a67d5d10a58cf38421446b735fd6ac567015b46f15c553c943420fd46f49f5df
|
3 |
+
size 78237
|
ppo-mountaincar-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:390c807bf570c7f8a749aa95d7bb1755c17d476c8b6abb02a65a3ad543c5ac9b
|
3 |
+
size 39873
|
ppo-mountaincar-v0/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-mountaincar-v0/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 sha256:97eba3bd512b7f19d1487de4ee4b6aa21f863a5aab593f6fbc2ee5865320f6dc
|
3 |
+
size 256015
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -89.2, "std_reward": 6.539113089708726, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T13:45:07.506731"}
|