Initial commit
Browse files- README.md +5 -0
- env_kwargs.yml +1 -1
- ppo-seals-Ant-v1.zip +2 -2
- ppo-seals-Ant-v1/_stable_baselines3_version +1 -1
- ppo-seals-Ant-v1/data +13 -13
- ppo-seals-Ant-v1/system_info.txt +1 -1
- replay.mp4 +3 -0
- results.json +1 -1
- train_eval_metrics.zip +1 -1
- vec_normalize.pkl +2 -2
README.md
CHANGED
@@ -86,3 +86,8 @@ OrderedDict([('batch_size', 16),
|
|
86 |
'norm_reward': True},
|
87 |
'norm_reward': False})])
|
88 |
```
|
|
|
|
|
|
|
|
|
|
|
|
86 |
'norm_reward': True},
|
87 |
'norm_reward': False})])
|
88 |
```
|
89 |
+
|
90 |
+
# Environment Arguments
|
91 |
+
```python
|
92 |
+
{'render_mode': 'rgb_array'}
|
93 |
+
```
|
env_kwargs.yml
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
render_mode: rgb_array
|
ppo-seals-Ant-v1.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 sha256:51fc02eaaa4465e781d9c6c8d43ce177c7d424717502ec438c139b9fcac1132f
|
3 |
+
size 187047
|
ppo-seals-Ant-v1/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
2.
|
|
|
1 |
+
2.2.0a3
|
ppo-seals-Ant-v1/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f1a8b6a5ee0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1a8b6a5f70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1a8b62a040>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1a8b62a0d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f1a8b62a160>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f1a8b62a1f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f1a8b62a280>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1a8b62a310>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f1a8b62a3a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1a8b62a430>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1a8b62a4c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1a8b62a550>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f1a8b6a3cc0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {
|
ppo-seals-Ant-v1/system_info.txt
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
|
2 |
- Python: 3.8.10
|
3 |
-
- Stable-Baselines3: 2.
|
4 |
- PyTorch: 2.0.1+cu117
|
5 |
- GPU Enabled: False
|
6 |
- Numpy: 1.24.4
|
|
|
1 |
- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
|
2 |
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 2.2.0a3
|
4 |
- PyTorch: 2.0.1+cu117
|
5 |
- GPU Enabled: False
|
6 |
- Numpy: 1.24.4
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53c5ddfbf8064dbe44959eed517d5f8a8ebb8f6145438e0b5483f38212bcdb25
|
3 |
+
size 1970797
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": 2461.2202511, "std_reward": 674.8025948179924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-
|
|
|
1 |
+
{"mean_reward": 2461.2202511, "std_reward": 674.8025948179924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-18T09:44:21.213699"}
|
train_eval_metrics.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 30489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d96f562eff810836192b8dc944d26ea9925821e78f2721fc945e64023b734254
|
3 |
size 30489
|
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:fba305e8d4b2577d1d6a5ac0b1ef7c61ae00ebaf02a868aa9f610a89844a0e8d
|
3 |
+
size 2285
|