Initial commit
Browse files- README.md +19 -7
- args.yml +11 -5
- config.yml +12 -2
- ppo-seals-MountainCar-v0.zip +2 -2
- ppo-seals-MountainCar-v0/_stable_baselines3_version +1 -1
- ppo-seals-MountainCar-v0/data +25 -24
- ppo-seals-MountainCar-v0/policy.optimizer.pth +1 -1
- ppo-seals-MountainCar-v0/policy.pth +2 -2
- ppo-seals-MountainCar-v0/system_info.txt +2 -2
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
- vec_normalize.pkl +2 -2
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value: -
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
@@ -37,15 +37,21 @@ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
|
37 |
|
38 |
```
|
39 |
# Download model and save it into the logs/ folder
|
40 |
-
python -m
|
41 |
python enjoy.py --algo ppo --env seals/MountainCar-v0 -f logs/
|
42 |
```
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
## Training (with the RL Zoo)
|
45 |
```
|
46 |
python train.py --algo ppo --env seals/MountainCar-v0 -f logs/
|
47 |
# Upload the model and generate video (when possible)
|
48 |
-
python -m
|
49 |
```
|
50 |
|
51 |
## Hyperparameters
|
@@ -61,11 +67,17 @@ OrderedDict([('batch_size', 512),
|
|
61 |
('n_epochs', 20),
|
62 |
('n_steps', 256),
|
63 |
('n_timesteps', 1000000.0),
|
64 |
-
('normalize',
|
|
|
65 |
('policy', 'MlpPolicy'),
|
66 |
('policy_kwargs',
|
67 |
-
'
|
68 |
-
|
|
|
69 |
('vf_coef', 0.25988158989488963),
|
70 |
-
('normalize_kwargs',
|
|
|
|
|
|
|
|
|
71 |
```
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: -123.10 +/- 25.47
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
37 |
|
38 |
```
|
39 |
# Download model and save it into the logs/ folder
|
40 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/MountainCar-v0 -orga HumanCompatibleAI -f logs/
|
41 |
python enjoy.py --algo ppo --env seals/MountainCar-v0 -f logs/
|
42 |
```
|
43 |
|
44 |
+
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
45 |
+
```
|
46 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/MountainCar-v0 -orga HumanCompatibleAI -f logs/
|
47 |
+
rl_zoo3 enjoy --algo ppo --env seals/MountainCar-v0 -f logs/
|
48 |
+
```
|
49 |
+
|
50 |
## Training (with the RL Zoo)
|
51 |
```
|
52 |
python train.py --algo ppo --env seals/MountainCar-v0 -f logs/
|
53 |
# Upload the model and generate video (when possible)
|
54 |
+
python -m rl_zoo3.push_to_hub --algo ppo --env seals/MountainCar-v0 -f logs/ -orga HumanCompatibleAI
|
55 |
```
|
56 |
|
57 |
## Hyperparameters
|
|
|
67 |
('n_epochs', 20),
|
68 |
('n_steps', 256),
|
69 |
('n_timesteps', 1000000.0),
|
70 |
+
('normalize',
|
71 |
+
{'gamma': 0.99, 'norm_obs': False, 'norm_reward': True}),
|
72 |
('policy', 'MlpPolicy'),
|
73 |
('policy_kwargs',
|
74 |
+
{'activation_fn': <class 'torch.nn.modules.activation.Tanh'>,
|
75 |
+
'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,
|
76 |
+
'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
|
77 |
('vf_coef', 0.25988158989488963),
|
78 |
+
('normalize_kwargs',
|
79 |
+
{'norm_obs': {'gamma': 0.99,
|
80 |
+
'norm_obs': False,
|
81 |
+
'norm_reward': True},
|
82 |
+
'norm_reward': False})])
|
83 |
```
|
args.yml
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - algo
|
3 |
- ppo
|
|
|
|
|
4 |
- - device
|
5 |
- cpu
|
6 |
- - env
|
@@ -16,7 +18,7 @@
|
|
16 |
- - hyperparams
|
17 |
- null
|
18 |
- - log_folder
|
19 |
-
-
|
20 |
- - log_interval
|
21 |
- -1
|
22 |
- - max_total_trials
|
@@ -41,6 +43,8 @@
|
|
41 |
- null
|
42 |
- - optimize_hyperparameters
|
43 |
- false
|
|
|
|
|
44 |
- - pruner
|
45 |
- median
|
46 |
- - sampler
|
@@ -50,13 +54,13 @@
|
|
50 |
- - save_replay_buffer
|
51 |
- false
|
52 |
- - seed
|
53 |
-
-
|
54 |
- - storage
|
55 |
- null
|
56 |
- - study_name
|
57 |
- null
|
58 |
- - tensorboard_log
|
59 |
-
- runs/seals/MountainCar-
|
60 |
- - track
|
61 |
- true
|
62 |
- - trained_agent
|
@@ -70,6 +74,8 @@
|
|
70 |
- - verbose
|
71 |
- 1
|
72 |
- - wandb_entity
|
73 |
-
-
|
74 |
- - wandb_project_name
|
75 |
-
- seals-experts-
|
|
|
|
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - algo
|
3 |
- ppo
|
4 |
+
- - conf_file
|
5 |
+
- hyperparams/python/ppo.py
|
6 |
- - device
|
7 |
- cpu
|
8 |
- - env
|
|
|
18 |
- - hyperparams
|
19 |
- null
|
20 |
- - log_folder
|
21 |
+
- logs
|
22 |
- - log_interval
|
23 |
- -1
|
24 |
- - max_total_trials
|
|
|
43 |
- null
|
44 |
- - optimize_hyperparameters
|
45 |
- false
|
46 |
+
- - progress
|
47 |
+
- false
|
48 |
- - pruner
|
49 |
- median
|
50 |
- - sampler
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 1
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
61 |
- null
|
62 |
- - tensorboard_log
|
63 |
+
- runs/seals/MountainCar-v0__ppo__1__1672653886
|
64 |
- - track
|
65 |
- true
|
66 |
- - trained_agent
|
|
|
74 |
- - verbose
|
75 |
- 1
|
76 |
- - wandb_entity
|
77 |
+
- ernestum
|
78 |
- - wandb_project_name
|
79 |
+
- seals-experts-normalized
|
80 |
+
- - yaml_file
|
81 |
+
- null
|
config.yml
CHANGED
@@ -22,10 +22,20 @@
|
|
22 |
- - n_timesteps
|
23 |
- 1000000.0
|
24 |
- - normalize
|
25 |
-
-
|
|
|
|
|
26 |
- - policy
|
27 |
- MlpPolicy
|
28 |
- - policy_kwargs
|
29 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
- - vf_coef
|
31 |
- 0.25988158989488963
|
|
|
22 |
- - n_timesteps
|
23 |
- 1000000.0
|
24 |
- - normalize
|
25 |
+
- gamma: 0.99
|
26 |
+
norm_obs: false
|
27 |
+
norm_reward: true
|
28 |
- - policy
|
29 |
- MlpPolicy
|
30 |
- - policy_kwargs
|
31 |
+
- activation_fn: !!python/name:torch.nn.modules.activation.Tanh ''
|
32 |
+
features_extractor_class: !!python/name:imitation.policies.base.NormalizeFeaturesExtractor ''
|
33 |
+
net_arch:
|
34 |
+
- pi:
|
35 |
+
- 64
|
36 |
+
- 64
|
37 |
+
vf:
|
38 |
+
- 64
|
39 |
+
- 64
|
40 |
- - vf_coef
|
41 |
- 0.25988158989488963
|
ppo-seals-MountainCar-v0.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c8715d54c5150bcde97ff97bc982740c295aa3d64e4b06b9682e3a56ebba8db
|
3 |
+
size 140740
|
ppo-seals-MountainCar-v0/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
1.6.
|
|
|
1 |
+
1.6.2
|
ppo-seals-MountainCar-v0/data
CHANGED
@@ -4,24 +4,24 @@
|
|
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
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {
|
23 |
":type:": "<class 'dict'>",
|
24 |
-
":serialized:": "
|
25 |
"activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
|
26 |
"net_arch": [
|
27 |
{
|
@@ -34,7 +34,8 @@
|
|
34 |
64
|
35 |
]
|
36 |
}
|
37 |
-
]
|
|
|
38 |
},
|
39 |
"observation_space": {
|
40 |
":type:": "<class 'gym.spaces.box.Box'>",
|
@@ -51,27 +52,27 @@
|
|
51 |
},
|
52 |
"action_space": {
|
53 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
54 |
-
":serialized:": "gAWVLwsAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
55 |
"n": 3,
|
56 |
"_shape": [],
|
57 |
"dtype": "int64",
|
58 |
"_np_random": "RandomState(MT19937)"
|
59 |
},
|
60 |
-
"n_envs":
|
61 |
"num_timesteps": 1003520,
|
62 |
"_total_timesteps": 1000000,
|
63 |
"_num_timesteps_at_start": 0,
|
64 |
-
"seed":
|
65 |
"action_noise": null,
|
66 |
-
"start_time":
|
67 |
"learning_rate": {
|
68 |
":type:": "<class 'function'>",
|
69 |
-
":serialized:": "
|
70 |
},
|
71 |
-
"tensorboard_log": "runs/seals/MountainCar-
|
72 |
"lr_schedule": {
|
73 |
":type:": "<class 'function'>",
|
74 |
-
":serialized:": "
|
75 |
},
|
76 |
"_last_obs": null,
|
77 |
"_last_episode_starts": {
|
@@ -80,7 +81,7 @@
|
|
80 |
},
|
81 |
"_last_original_obs": {
|
82 |
":type:": "<class 'numpy.ndarray'>",
|
83 |
-
":serialized:": "
|
84 |
},
|
85 |
"_episode_num": 0,
|
86 |
"use_sde": false,
|
@@ -88,7 +89,7 @@
|
|
88 |
"_current_progress_remaining": -0.0035199999999999676,
|
89 |
"ep_info_buffer": {
|
90 |
":type:": "<class 'collections.deque'>",
|
91 |
-
":serialized:": "
|
92 |
},
|
93 |
"ep_success_buffer": {
|
94 |
":type:": "<class 'collections.deque'>",
|
@@ -105,7 +106,7 @@
|
|
105 |
"n_epochs": 20,
|
106 |
"clip_range": {
|
107 |
":type:": "<class 'function'>",
|
108 |
-
":serialized:": "
|
109 |
},
|
110 |
"clip_range_vf": null,
|
111 |
"normalize_advantage": true,
|
|
|
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 0x7faed9aed790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faed9aed820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faed9aed8b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faed9aed940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7faed9aed9d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7faed9aeda60>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faed9aedaf0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7faed9aedb80>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faed9aedc10>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faed9aedca0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7faed9aedd30>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7faed9ae4c30>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {
|
23 |
":type:": "<class 'dict'>",
|
24 |
+
":serialized:": "gAWVvAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldWGMGGZlYXR1cmVzX2V4dHJhY3Rvcl9jbGFzc5SMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwaTm9ybWFsaXplRmVhdHVyZXNFeHRyYWN0b3KUk5R1Lg==",
|
25 |
"activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
|
26 |
"net_arch": [
|
27 |
{
|
|
|
34 |
64
|
35 |
]
|
36 |
}
|
37 |
+
],
|
38 |
+
"features_extractor_class": "<class 'imitation.policies.base.NormalizeFeaturesExtractor'>"
|
39 |
},
|
40 |
"observation_space": {
|
41 |
":type:": "<class 'gym.spaces.box.Box'>",
|
|
|
52 |
},
|
53 |
"action_space": {
|
54 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
55 |
+
":serialized:": "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",
|
56 |
"n": 3,
|
57 |
"_shape": [],
|
58 |
"dtype": "int64",
|
59 |
"_np_random": "RandomState(MT19937)"
|
60 |
},
|
61 |
+
"n_envs": 1,
|
62 |
"num_timesteps": 1003520,
|
63 |
"_total_timesteps": 1000000,
|
64 |
"_num_timesteps_at_start": 0,
|
65 |
+
"seed": 4,
|
66 |
"action_noise": null,
|
67 |
+
"start_time": 1672653888502052346,
|
68 |
"learning_rate": {
|
69 |
":type:": "<class 'function'>",
|
70 |
+
":serialized:": "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"
|
71 |
},
|
72 |
+
"tensorboard_log": "runs/seals/MountainCar-v0__ppo__1__1672653886/seals-MountainCar-v0",
|
73 |
"lr_schedule": {
|
74 |
":type:": "<class 'function'>",
|
75 |
+
":serialized:": "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"
|
76 |
},
|
77 |
"_last_obs": null,
|
78 |
"_last_episode_starts": {
|
|
|
81 |
},
|
82 |
"_last_original_obs": {
|
83 |
":type:": "<class 'numpy.ndarray'>",
|
84 |
+
":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAPKF4L4AAAAArHrcvgAAAADko+i+AAAAAB7z5b4AAAAAyykTvwAAAADv6Ae/AAAAACWCC78AAAAAWPLvvgAAAACS0gK/AAAAAGl+9r4AAAAAYqkAvwAAAAALSQS/AAAAANWE7b4AAAAAo+gTvwAAAABIX9++AAAAAE8Pzr4AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
|
85 |
},
|
86 |
"_episode_num": 0,
|
87 |
"use_sde": false,
|
|
|
89 |
"_current_progress_remaining": -0.0035199999999999676,
|
90 |
"ep_info_buffer": {
|
91 |
":type:": "<class 'collections.deque'>",
|
92 |
+
":serialized:": "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"
|
93 |
},
|
94 |
"ep_success_buffer": {
|
95 |
":type:": "<class 'collections.deque'>",
|
|
|
106 |
"n_epochs": 20,
|
107 |
"clip_range": {
|
108 |
":type:": "<class 'function'>",
|
109 |
+
":serialized:": "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"
|
110 |
},
|
111 |
"clip_range_vf": null,
|
112 |
"normalize_advantage": true,
|
ppo-seals-MountainCar-v0/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 80889
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d37d94b78301e5971ad05c3a5a012d6519a32e0fb8250eb425a9d01e06145e45
|
3 |
size 80889
|
ppo-seals-MountainCar-v0/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec8b2e9cc43bb7d40aae3cb3c2038dd7706e4167c592da2dead776535b2ad991
|
3 |
+
size 40760
|
ppo-seals-MountainCar-v0/system_info.txt
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
-
OS: Linux-5.4.0-
|
2 |
Python: 3.8.10
|
3 |
-
Stable-Baselines3: 1.6.
|
4 |
PyTorch: 1.11.0+cu102
|
5 |
GPU Enabled: False
|
6 |
Numpy: 1.22.3
|
|
|
1 |
+
OS: Linux-5.4.0-125-generic-x86_64-with-glibc2.29 #141-Ubuntu SMP Wed Aug 10 13:42:03 UTC 2022
|
2 |
Python: 3.8.10
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
PyTorch: 1.11.0+cu102
|
5 |
GPU Enabled: False
|
6 |
Numpy: 1.22.3
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7097a70af23f56753ff4df18b7f212fdf859e8752a93846482e5612ca1c5146f
|
3 |
+
size 176520
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -123.1, "std_reward": 25.469393396781165, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T11:15:35.759802"}
|
train_eval_metrics.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11a94a0f3d92cc83a61ceb6f582f592dcf8c50a0b55aef0d6d4d6d374381341e
|
3 |
+
size 119305
|
vec_normalize.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17b0e58a05e432df8b67646a4caaf35e57a93ff193b4023911c74e0b141364ef
|
3 |
+
size 3961
|