Initial commit
Browse files- .gitattributes +1 -0
- README.md +89 -0
- args.yml +81 -0
- config.yml +41 -0
- env_kwargs.yml +1 -0
- ppo-seals-HalfCheetah-v1.zip +3 -0
- ppo-seals-HalfCheetah-v1/_stable_baselines3_version +1 -0
- ppo-seals-HalfCheetah-v1/data +123 -0
- ppo-seals-HalfCheetah-v1/policy.optimizer.pth +3 -0
- ppo-seals-HalfCheetah-v1/policy.pth +3 -0
- ppo-seals-HalfCheetah-v1/pytorch_variables.pth +3 -0
- ppo-seals-HalfCheetah-v1/system_info.txt +9 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
- vec_normalize.pkl +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- seals/HalfCheetah-v1
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: seals/HalfCheetah-v1
|
16 |
+
type: seals/HalfCheetah-v1
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 1675.76 +/- 45.89
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **seals/HalfCheetah-v1**
|
25 |
+
This is a trained model of a **PPO** agent playing **seals/HalfCheetah-v1**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
27 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
28 |
+
|
29 |
+
The RL Zoo is a training framework for Stable Baselines3
|
30 |
+
reinforcement learning agents,
|
31 |
+
with hyperparameter optimization and pre-trained agents included.
|
32 |
+
|
33 |
+
## Usage (with SB3 RL Zoo)
|
34 |
+
|
35 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
36 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
37 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
38 |
+
|
39 |
+
Install the RL Zoo (with SB3 and SB3-Contrib):
|
40 |
+
```bash
|
41 |
+
pip install rl_zoo3
|
42 |
+
```
|
43 |
+
|
44 |
+
```
|
45 |
+
# Download model and save it into the logs/ folder
|
46 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/HalfCheetah-v1 -orga ernestum -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo ppo --env seals/HalfCheetah-v1 -f logs/
|
48 |
+
```
|
49 |
+
|
50 |
+
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
51 |
+
```
|
52 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/HalfCheetah-v1 -orga ernestum -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo ppo --env seals/HalfCheetah-v1 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo ppo --env seals/HalfCheetah-v1 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo ppo --env seals/HalfCheetah-v1 -f logs/ -orga ernestum
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('batch_size', 64),
|
66 |
+
('clip_range', 0.1),
|
67 |
+
('ent_coef', 3.794797423594763e-06),
|
68 |
+
('gae_lambda', 0.95),
|
69 |
+
('gamma', 0.95),
|
70 |
+
('learning_rate', 0.0003286871805949382),
|
71 |
+
('max_grad_norm', 0.8),
|
72 |
+
('n_envs', 1),
|
73 |
+
('n_epochs', 5),
|
74 |
+
('n_steps', 512),
|
75 |
+
('n_timesteps', 1000000.0),
|
76 |
+
('normalize',
|
77 |
+
{'gamma': 0.95, 'norm_obs': False, 'norm_reward': True}),
|
78 |
+
('policy', 'MlpPolicy'),
|
79 |
+
('policy_kwargs',
|
80 |
+
{'activation_fn': <class 'torch.nn.modules.activation.Tanh'>,
|
81 |
+
'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,
|
82 |
+
'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
|
83 |
+
('vf_coef', 0.11483689492120866),
|
84 |
+
('normalize_kwargs',
|
85 |
+
{'norm_obs': {'gamma': 0.95,
|
86 |
+
'norm_obs': False,
|
87 |
+
'norm_reward': True},
|
88 |
+
'norm_reward': False})])
|
89 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- ppo
|
4 |
+
- - conf_file
|
5 |
+
- hyperparams/python/ppo.py
|
6 |
+
- - device
|
7 |
+
- cpu
|
8 |
+
- - env
|
9 |
+
- seals/HalfCheetah-v1
|
10 |
+
- - env_kwargs
|
11 |
+
- null
|
12 |
+
- - eval_episodes
|
13 |
+
- 0
|
14 |
+
- - eval_freq
|
15 |
+
- 25000
|
16 |
+
- - gym_packages
|
17 |
+
- - seals
|
18 |
+
- - hyperparams
|
19 |
+
- null
|
20 |
+
- - log_folder
|
21 |
+
- gymnasium_models
|
22 |
+
- - log_interval
|
23 |
+
- -1
|
24 |
+
- - max_total_trials
|
25 |
+
- null
|
26 |
+
- - n_eval_envs
|
27 |
+
- 1
|
28 |
+
- - n_evaluations
|
29 |
+
- null
|
30 |
+
- - n_jobs
|
31 |
+
- 1
|
32 |
+
- - n_startup_trials
|
33 |
+
- 10
|
34 |
+
- - n_timesteps
|
35 |
+
- -1
|
36 |
+
- - n_trials
|
37 |
+
- 500
|
38 |
+
- - no_optim_plots
|
39 |
+
- false
|
40 |
+
- - num_threads
|
41 |
+
- 4
|
42 |
+
- - optimization_log_path
|
43 |
+
- null
|
44 |
+
- - optimize_hyperparameters
|
45 |
+
- false
|
46 |
+
- - progress
|
47 |
+
- false
|
48 |
+
- - pruner
|
49 |
+
- median
|
50 |
+
- - sampler
|
51 |
+
- tpe
|
52 |
+
- - save_freq
|
53 |
+
- -1
|
54 |
+
- - save_replay_buffer
|
55 |
+
- false
|
56 |
+
- - seed
|
57 |
+
- 1446304544
|
58 |
+
- - storage
|
59 |
+
- null
|
60 |
+
- - study_name
|
61 |
+
- null
|
62 |
+
- - tensorboard_log
|
63 |
+
- ''
|
64 |
+
- - track
|
65 |
+
- false
|
66 |
+
- - trained_agent
|
67 |
+
- ''
|
68 |
+
- - truncate_last_trajectory
|
69 |
+
- true
|
70 |
+
- - uuid
|
71 |
+
- false
|
72 |
+
- - vec_env
|
73 |
+
- dummy
|
74 |
+
- - verbose
|
75 |
+
- 1
|
76 |
+
- - wandb_entity
|
77 |
+
- null
|
78 |
+
- - wandb_project_name
|
79 |
+
- sb3
|
80 |
+
- - wandb_tags
|
81 |
+
- []
|
config.yml
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 64
|
4 |
+
- - clip_range
|
5 |
+
- 0.1
|
6 |
+
- - ent_coef
|
7 |
+
- 3.794797423594763e-06
|
8 |
+
- - gae_lambda
|
9 |
+
- 0.95
|
10 |
+
- - gamma
|
11 |
+
- 0.95
|
12 |
+
- - learning_rate
|
13 |
+
- 0.0003286871805949382
|
14 |
+
- - max_grad_norm
|
15 |
+
- 0.8
|
16 |
+
- - n_envs
|
17 |
+
- 1
|
18 |
+
- - n_epochs
|
19 |
+
- 5
|
20 |
+
- - n_steps
|
21 |
+
- 512
|
22 |
+
- - n_timesteps
|
23 |
+
- 1000000.0
|
24 |
+
- - normalize
|
25 |
+
- gamma: 0.95
|
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 |
+
- 0.11483689492120866
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
ppo-seals-HalfCheetah-v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de340d87b24482ffa2ffd98bfda8bcaf7a4f487b67624d4308dcdcf40d188756
|
3 |
+
size 167929
|
ppo-seals-HalfCheetah-v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.1.0
|
ppo-seals-HalfCheetah-v1/data
ADDED
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 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 0x7f9610075040>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f96100750d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9610075160>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f96100751f0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9610075280>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9610075310>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f96100753a0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9610075430>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f96100754c0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9610075550>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f96100755e0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9610075670>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f9610051ae0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {
|
24 |
+
":type:": "<class 'dict'>",
|
25 |
+
":serialized:": "gAWVuQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEtAS0BljAJ2ZpRdlChLQEtAZXWMGGZlYXR1cmVzX2V4dHJhY3Rvcl9jbGFzc5SMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwaTm9ybWFsaXplRmVhdHVyZXNFeHRyYWN0b3KUk5R1Lg==",
|
26 |
+
"activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
|
27 |
+
"net_arch": {
|
28 |
+
"pi": [
|
29 |
+
64,
|
30 |
+
64
|
31 |
+
],
|
32 |
+
"vf": [
|
33 |
+
64,
|
34 |
+
64
|
35 |
+
]
|
36 |
+
},
|
37 |
+
"features_extractor_class": "<class 'imitation.policies.base.NormalizeFeaturesExtractor'>"
|
38 |
+
},
|
39 |
+
"num_timesteps": 1000448,
|
40 |
+
"_total_timesteps": 1000000,
|
41 |
+
"_num_timesteps_at_start": 0,
|
42 |
+
"seed": 0,
|
43 |
+
"action_noise": null,
|
44 |
+
"start_time": 1694771152556178530,
|
45 |
+
"learning_rate": {
|
46 |
+
":type:": "<class 'function'>",
|
47 |
+
":serialized:": "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"
|
48 |
+
},
|
49 |
+
"tensorboard_log": null,
|
50 |
+
"_last_obs": null,
|
51 |
+
"_last_episode_starts": {
|
52 |
+
":type:": "<class 'numpy.ndarray'>",
|
53 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
54 |
+
},
|
55 |
+
"_last_original_obs": {
|
56 |
+
":type:": "<class 'numpy.ndarray'>",
|
57 |
+
":serialized:": "gAWVBQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaQAAAAAAAAACjGfK/XCJQ/IKV/QyFJlD+XR2iGCdqtv3og2uygu7O/2Fne9nRChL84DRNEU/KYvwj7Cx0iFqw/911oR5MJqb+0MBExINOUvwwlKjRtirk/BC2EDH1Bh79UtxuGx2u8v0KEwHLD7MG/uAKDXRq1mj9wmFPvkpkWvygLSj5P870/G+SEKGdqqD+0NSo+WzquP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsShpSMAUOUdJRSlC4="
|
58 |
+
},
|
59 |
+
"_episode_num": 0,
|
60 |
+
"use_sde": false,
|
61 |
+
"sde_sample_freq": -1,
|
62 |
+
"_current_progress_remaining": -0.00044800000000000395,
|
63 |
+
"_stats_window_size": 100,
|
64 |
+
"ep_info_buffer": {
|
65 |
+
":type:": "<class 'collections.deque'>",
|
66 |
+
":serialized:": "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"
|
67 |
+
},
|
68 |
+
"ep_success_buffer": {
|
69 |
+
":type:": "<class 'collections.deque'>",
|
70 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
71 |
+
},
|
72 |
+
"_n_updates": 9770,
|
73 |
+
"observation_space": {
|
74 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
75 |
+
":serialized:": "gAWVvQIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLEoWUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBAolhIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgUSxKFlGgYdJRSlIwGX3NoYXBllEsShZSMA2xvd5RoECiWkAAAAAAAAAAAAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P+UaApLEoWUaBh0lFKUjARoaWdolGgQKJaQAAAAAAAAAAAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwf5RoCksShZRoGHSUUpSMCGxvd19yZXBylIwELWluZpSMCWhpZ2hfcmVwcpSMA2luZpSMCl9ucF9yYW5kb22UTnViLg==",
|
76 |
+
"dtype": "float64",
|
77 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False]",
|
78 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False]",
|
79 |
+
"_shape": [
|
80 |
+
18
|
81 |
+
],
|
82 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf]",
|
83 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]",
|
84 |
+
"low_repr": "-inf",
|
85 |
+
"high_repr": "inf",
|
86 |
+
"_np_random": null
|
87 |
+
},
|
88 |
+
"action_space": {
|
89 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
90 |
+
":serialized:": "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",
|
91 |
+
"dtype": "float32",
|
92 |
+
"bounded_below": "[ True True True True True True]",
|
93 |
+
"bounded_above": "[ True True True True True True]",
|
94 |
+
"_shape": [
|
95 |
+
6
|
96 |
+
],
|
97 |
+
"low": "[-1. -1. -1. -1. -1. -1.]",
|
98 |
+
"high": "[1. 1. 1. 1. 1. 1.]",
|
99 |
+
"low_repr": "-1.0",
|
100 |
+
"high_repr": "1.0",
|
101 |
+
"_np_random": "Generator(PCG64)"
|
102 |
+
},
|
103 |
+
"n_envs": 1,
|
104 |
+
"n_steps": 512,
|
105 |
+
"gamma": 0.95,
|
106 |
+
"gae_lambda": 0.95,
|
107 |
+
"ent_coef": 3.794797423594763e-06,
|
108 |
+
"vf_coef": 0.11483689492120866,
|
109 |
+
"max_grad_norm": 0.8,
|
110 |
+
"batch_size": 64,
|
111 |
+
"n_epochs": 5,
|
112 |
+
"clip_range": {
|
113 |
+
":type:": "<class 'function'>",
|
114 |
+
":serialized:": "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"
|
115 |
+
},
|
116 |
+
"clip_range_vf": null,
|
117 |
+
"normalize_advantage": true,
|
118 |
+
"target_kl": null,
|
119 |
+
"lr_schedule": {
|
120 |
+
":type:": "<class 'function'>",
|
121 |
+
":serialized:": "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"
|
122 |
+
}
|
123 |
+
}
|
ppo-seals-HalfCheetah-v1/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d954d7c863e9871fc88a1b2a821f9d27918b2951b4e7fe0db61ab95f94bb9880
|
3 |
+
size 99568
|
ppo-seals-HalfCheetah-v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63ecc77265ba77e1df81323ae8a900c8251f939ed6cff8b5c742dedb389fa19f
|
3 |
+
size 50933
|
ppo-seals-HalfCheetah-v1/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-seals-HalfCheetah-v1/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 2.1.0
|
4 |
+
- PyTorch: 2.0.1+cu117
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.24.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.29.1
|
9 |
+
- OpenAI Gym: 0.21.0
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 1675.7591266, "std_reward": 45.89236738692049, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:52:34.059673"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff261ae7fec70ee5255dd71922e72352cd5577848679947329dc99ed9ad7bdfa
|
3 |
+
size 29887
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0711c3695bb1f0b999b085d3a9454100050b3d838539e2c937cd26011a17a691
|
3 |
+
size 1968
|