Initial commit
Browse files- README.md +19 -7
- args.yml +10 -4
- config.yml +12 -2
- ppo-seals-Ant-v0.zip +2 -2
- ppo-seals-Ant-v0/_stable_baselines3_version +1 -1
- ppo-seals-Ant-v0/data +23 -22
- ppo-seals-Ant-v0/policy.optimizer.pth +2 -2
- ppo-seals-Ant-v0/policy.pth +2 -2
- ppo-seals-Ant-v0/system_info.txt +2 -2
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
- vec_normalize.pkl +3 -0
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/Ant-v0 -f logs/
|
42 |
```
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
## Training (with the RL Zoo)
|
45 |
```
|
46 |
python train.py --algo ppo --env seals/Ant-v0 -f logs/
|
47 |
# Upload the model and generate video (when possible)
|
48 |
-
python -m
|
49 |
```
|
50 |
|
51 |
## Hyperparameters
|
@@ -60,11 +66,17 @@ OrderedDict([('batch_size', 16),
|
|
60 |
('n_epochs', 10),
|
61 |
('n_steps', 2048),
|
62 |
('n_timesteps', 1000000.0),
|
63 |
-
('normalize',
|
|
|
64 |
('policy', 'MlpPolicy'),
|
65 |
('policy_kwargs',
|
66 |
-
'
|
67 |
-
|
|
|
68 |
('vf_coef', 0.4351450387648799),
|
69 |
-
('normalize_kwargs',
|
|
|
|
|
|
|
|
|
70 |
```
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 3034.50 +/- 1124.70
|
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/Ant-v0 -orga HumanCompatibleAI -f logs/
|
41 |
python enjoy.py --algo ppo --env seals/Ant-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/Ant-v0 -orga HumanCompatibleAI -f logs/
|
47 |
+
rl_zoo3 enjoy --algo ppo --env seals/Ant-v0 -f logs/
|
48 |
+
```
|
49 |
+
|
50 |
## Training (with the RL Zoo)
|
51 |
```
|
52 |
python train.py --algo ppo --env seals/Ant-v0 -f logs/
|
53 |
# Upload the model and generate video (when possible)
|
54 |
+
python -m rl_zoo3.push_to_hub --algo ppo --env seals/Ant-v0 -f logs/ -orga HumanCompatibleAI
|
55 |
```
|
56 |
|
57 |
## Hyperparameters
|
|
|
66 |
('n_epochs', 10),
|
67 |
('n_steps', 2048),
|
68 |
('n_timesteps', 1000000.0),
|
69 |
+
('normalize',
|
70 |
+
{'gamma': 0.995, 'norm_obs': False, 'norm_reward': True}),
|
71 |
('policy', 'MlpPolicy'),
|
72 |
('policy_kwargs',
|
73 |
+
{'activation_fn': <class 'torch.nn.modules.activation.Tanh'>,
|
74 |
+
'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,
|
75 |
+
'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
|
76 |
('vf_coef', 0.4351450387648799),
|
77 |
+
('normalize_kwargs',
|
78 |
+
{'norm_obs': {'gamma': 0.995,
|
79 |
+
'norm_obs': False,
|
80 |
+
'norm_reward': True},
|
81 |
+
'norm_reward': False})])
|
82 |
```
|
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
|
@@ -56,7 +60,7 @@
|
|
56 |
- - study_name
|
57 |
- null
|
58 |
- - tensorboard_log
|
59 |
-
- runs/seals/Ant-
|
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
|
|
|
60 |
- - study_name
|
61 |
- null
|
62 |
- - tensorboard_log
|
63 |
+
- runs/seals/Ant-v0__ppo__6__1670517965
|
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
@@ -20,10 +20,20 @@
|
|
20 |
- - n_timesteps
|
21 |
- 1000000.0
|
22 |
- - normalize
|
23 |
-
-
|
|
|
|
|
24 |
- - policy
|
25 |
- MlpPolicy
|
26 |
- - policy_kwargs
|
27 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
- - vf_coef
|
29 |
- 0.4351450387648799
|
|
|
20 |
- - n_timesteps
|
21 |
- 1000000.0
|
22 |
- - normalize
|
23 |
+
- gamma: 0.995
|
24 |
+
norm_obs: false
|
25 |
+
norm_reward: true
|
26 |
- - policy
|
27 |
- MlpPolicy
|
28 |
- - policy_kwargs
|
29 |
+
- activation_fn: !!python/name:torch.nn.modules.activation.Tanh ''
|
30 |
+
features_extractor_class: !!python/name:imitation.policies.base.NormalizeFeaturesExtractor ''
|
31 |
+
net_arch:
|
32 |
+
- pi:
|
33 |
+
- 64
|
34 |
+
- 64
|
35 |
+
vf:
|
36 |
+
- 64
|
37 |
+
- 64
|
38 |
- - vf_coef
|
39 |
- 0.4351450387648799
|
ppo-seals-Ant-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 sha256:1a6b9a42330bc2c39b68b9f94073db60c819a5ff57b5b22c59a05733f9d66b71
|
3 |
+
size 325290
|
ppo-seals-Ant-v0/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
1.6.
|
|
|
1 |
+
1.6.2
|
ppo-seals-Ant-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'>",
|
@@ -51,7 +52,7 @@
|
|
51 |
},
|
52 |
"action_space": {
|
53 |
":type:": "<class 'gym.spaces.box.Box'>",
|
54 |
-
":serialized:": "gAWVJwwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAIC/AACAvwAAgL8AAIC/AACAvwAAgL8AAIC/AACAv5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/AACAP5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAQEBAQEBAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////
|
55 |
"dtype": "float32",
|
56 |
"_shape": [
|
57 |
8
|
@@ -66,17 +67,17 @@
|
|
66 |
"num_timesteps": 1001472,
|
67 |
"_total_timesteps": 1000000,
|
68 |
"_num_timesteps_at_start": 0,
|
69 |
-
"seed":
|
70 |
"action_noise": null,
|
71 |
-
"start_time":
|
72 |
"learning_rate": {
|
73 |
":type:": "<class 'function'>",
|
74 |
-
":serialized:": "
|
75 |
},
|
76 |
-
"tensorboard_log": "runs/seals/Ant-
|
77 |
"lr_schedule": {
|
78 |
":type:": "<class 'function'>",
|
79 |
-
":serialized:": "
|
80 |
},
|
81 |
"_last_obs": null,
|
82 |
"_last_episode_starts": {
|
@@ -93,7 +94,7 @@
|
|
93 |
"_current_progress_remaining": -0.0014719999999999178,
|
94 |
"ep_info_buffer": {
|
95 |
":type:": "<class 'collections.deque'>",
|
96 |
-
":serialized:": "gAWVgRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
97 |
},
|
98 |
"ep_success_buffer": {
|
99 |
":type:": "<class 'collections.deque'>",
|
@@ -110,7 +111,7 @@
|
|
110 |
"n_epochs": 10,
|
111 |
"clip_range": {
|
112 |
":type:": "<class 'function'>",
|
113 |
-
":serialized:": "
|
114 |
},
|
115 |
"clip_range_vf": null,
|
116 |
"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 0x7f3eaaac4700>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3eaaac4790>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3eaaac4820>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3eaaac48b0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3eaaac4940>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3eaaac49d0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3eaaac4a60>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3eaaac4af0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3eaaac4b80>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3eaaac4c10>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3eaaac4ca0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f3eaaabcbd0>"
|
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.box.Box'>",
|
55 |
+
":serialized:": "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",
|
56 |
"dtype": "float32",
|
57 |
"_shape": [
|
58 |
8
|
|
|
67 |
"num_timesteps": 1001472,
|
68 |
"_total_timesteps": 1000000,
|
69 |
"_num_timesteps_at_start": 0,
|
70 |
+
"seed": 6,
|
71 |
"action_noise": null,
|
72 |
+
"start_time": 1670518056075171587,
|
73 |
"learning_rate": {
|
74 |
":type:": "<class 'function'>",
|
75 |
+
":serialized:": "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"
|
76 |
},
|
77 |
+
"tensorboard_log": "runs/seals/Ant-v0__ppo__6__1670517965/seals-Ant-v0",
|
78 |
"lr_schedule": {
|
79 |
":type:": "<class 'function'>",
|
80 |
+
":serialized:": "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"
|
81 |
},
|
82 |
"_last_obs": null,
|
83 |
"_last_episode_starts": {
|
|
|
94 |
"_current_progress_remaining": -0.0014719999999999178,
|
95 |
"ep_info_buffer": {
|
96 |
":type:": "<class 'collections.deque'>",
|
97 |
+
":serialized:": "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"
|
98 |
},
|
99 |
"ep_success_buffer": {
|
100 |
":type:": "<class 'collections.deque'>",
|
|
|
111 |
"n_epochs": 10,
|
112 |
"clip_range": {
|
113 |
":type:": "<class 'function'>",
|
114 |
+
":serialized:": "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"
|
115 |
},
|
116 |
"clip_range_vf": null,
|
117 |
"normalize_advantage": true,
|
ppo-seals-Ant-v0/policy.optimizer.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 sha256:9f5ac25062e51075852b070bf4c27491cf48b1397933dba278a543931efd63ee
|
3 |
+
size 197872
|
ppo-seals-Ant-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 sha256:3642052a35b9285abc3164dcdf69e7694b38d217df440b517ae3369af4800974
|
3 |
+
size 100085
|
ppo-seals-Ant-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 sha256:335bdab2ffdcf2cebfead90745a0f9e3eada21265d248f3ea6c8f96970b9ef3c
|
3 |
+
size 1831582
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 3034.4950357, "std_reward": 1124.69662303982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T14:29:02.930842"}
|
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:f6ef0fab686049a2bbf9661ac7176caf4cb4865b4442af59e2b30c1d0e0a3bd1
|
3 |
+
size 34017
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2adb406c0bd0bdb92ece065dd4c10c63fff163f83a781d12e93a8639204503ac
|
3 |
+
size 6872
|