Initial commit
Browse files- .gitattributes +2 -0
- README.md +74 -0
- args.yml +59 -0
- config.yml +38 -0
- env_kwargs.yml +1 -0
- ppo-AntBulletEnv-v0.zip +3 -0
- ppo-AntBulletEnv-v0/_stable_baselines3_version +1 -0
- ppo-AntBulletEnv-v0/data +121 -0
- ppo-AntBulletEnv-v0/policy.optimizer.pth +3 -0
- ppo-AntBulletEnv-v0/policy.pth +3 -0
- ppo-AntBulletEnv-v0/pytorch_variables.pth +3 -0
- ppo-AntBulletEnv-v0/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
- vec_normalize.pkl +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,5 @@ 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
|
29 |
+
vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- AntBulletEnv-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: 2878.40 +/- 58.20
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: AntBulletEnv-v0
|
20 |
+
type: AntBulletEnv-v0
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **AntBulletEnv-v0**
|
24 |
+
This is a trained model of a **PPO** agent playing **AntBulletEnv-v0**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
26 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
27 |
+
|
28 |
+
The RL Zoo is a training framework for Stable Baselines3
|
29 |
+
reinforcement learning agents,
|
30 |
+
with hyperparameter optimization and pre-trained agents included.
|
31 |
+
|
32 |
+
## Usage (with SB3 RL Zoo)
|
33 |
+
|
34 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
35 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
36 |
+
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 utils.load_from_hub --algo ppo --env AntBulletEnv-v0 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo ppo --env AntBulletEnv-v0 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo ppo --env AntBulletEnv-v0 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo ppo --env AntBulletEnv-v0 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('batch_size', 128),
|
54 |
+
('clip_range', 0.4),
|
55 |
+
('ent_coef', 0.0),
|
56 |
+
('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
|
57 |
+
('gae_lambda', 0.9),
|
58 |
+
('gamma', 0.99),
|
59 |
+
('learning_rate', 3e-05),
|
60 |
+
('max_grad_norm', 0.5),
|
61 |
+
('n_envs', 16),
|
62 |
+
('n_epochs', 20),
|
63 |
+
('n_steps', 512),
|
64 |
+
('n_timesteps', 2000000.0),
|
65 |
+
('normalize', True),
|
66 |
+
('policy', 'MlpPolicy'),
|
67 |
+
('policy_kwargs',
|
68 |
+
'dict(log_std_init=-1, ortho_init=False, activation_fn=nn.ReLU, '
|
69 |
+
'net_arch=[dict(pi=[256, 256], vf=[256, 256])] )'),
|
70 |
+
('sde_sample_freq', 4),
|
71 |
+
('use_sde', True),
|
72 |
+
('vf_coef', 0.5),
|
73 |
+
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
|
74 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- ppo
|
4 |
+
- - env
|
5 |
+
- AntBulletEnv-v0
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 10
|
10 |
+
- - eval_freq
|
11 |
+
- 10000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- null
|
16 |
+
- - log_folder
|
17 |
+
- rl-trained-agents/
|
18 |
+
- - log_interval
|
19 |
+
- -1
|
20 |
+
- - n_evaluations
|
21 |
+
- 20
|
22 |
+
- - n_jobs
|
23 |
+
- 1
|
24 |
+
- - n_startup_trials
|
25 |
+
- 10
|
26 |
+
- - n_timesteps
|
27 |
+
- -1
|
28 |
+
- - n_trials
|
29 |
+
- 10
|
30 |
+
- - num_threads
|
31 |
+
- -1
|
32 |
+
- - optimize_hyperparameters
|
33 |
+
- false
|
34 |
+
- - pruner
|
35 |
+
- median
|
36 |
+
- - sampler
|
37 |
+
- tpe
|
38 |
+
- - save_freq
|
39 |
+
- -1
|
40 |
+
- - save_replay_buffer
|
41 |
+
- false
|
42 |
+
- - seed
|
43 |
+
- 1239483580
|
44 |
+
- - storage
|
45 |
+
- null
|
46 |
+
- - study_name
|
47 |
+
- null
|
48 |
+
- - tensorboard_log
|
49 |
+
- ''
|
50 |
+
- - trained_agent
|
51 |
+
- ''
|
52 |
+
- - truncate_last_trajectory
|
53 |
+
- true
|
54 |
+
- - uuid
|
55 |
+
- true
|
56 |
+
- - vec_env
|
57 |
+
- dummy
|
58 |
+
- - verbose
|
59 |
+
- 1
|
config.yml
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 128
|
4 |
+
- - clip_range
|
5 |
+
- 0.4
|
6 |
+
- - ent_coef
|
7 |
+
- 0.0
|
8 |
+
- - env_wrapper
|
9 |
+
- sb3_contrib.common.wrappers.TimeFeatureWrapper
|
10 |
+
- - gae_lambda
|
11 |
+
- 0.9
|
12 |
+
- - gamma
|
13 |
+
- 0.99
|
14 |
+
- - learning_rate
|
15 |
+
- 3.0e-05
|
16 |
+
- - max_grad_norm
|
17 |
+
- 0.5
|
18 |
+
- - n_envs
|
19 |
+
- 16
|
20 |
+
- - n_epochs
|
21 |
+
- 20
|
22 |
+
- - n_steps
|
23 |
+
- 512
|
24 |
+
- - n_timesteps
|
25 |
+
- 2000000.0
|
26 |
+
- - normalize
|
27 |
+
- true
|
28 |
+
- - policy
|
29 |
+
- MlpPolicy
|
30 |
+
- - policy_kwargs
|
31 |
+
- dict(log_std_init=-1, ortho_init=False, activation_fn=nn.ReLU, net_arch=[dict(pi=[256,
|
32 |
+
256], vf=[256, 256])] )
|
33 |
+
- - sde_sample_freq
|
34 |
+
- 4
|
35 |
+
- - use_sde
|
36 |
+
- true
|
37 |
+
- - vf_coef
|
38 |
+
- 0.5
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
ppo-AntBulletEnv-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd3edca35a73ed43ab363c3065cede45e4e1805e28b75b77be8d66ffcc262f48
|
3 |
+
size 1850373
|
ppo-AntBulletEnv-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
ppo-AntBulletEnv-v0/data
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f68a7e13950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f68a7e139e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f68a7e13a70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f68a7e13b00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f68a7e13b90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f68a7e13c20>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f68a7e13cb0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f68a7e13d40>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f68a7e13dd0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f68a7e13e60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f68a7e13ef0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f68a7e64840>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {
|
23 |
+
":type:": "<class 'dict'>",
|
24 |
+
":serialized:": "gASVjgAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/////4wKb3J0aG9faW5pdJSJjA1hY3RpdmF0aW9uX2ZulIwbdG9yY2gubm4ubW9kdWxlcy5hY3RpdmF0aW9ulIwEUmVMVZSTlIwIbmV0X2FyY2iUXZR9lCiMAnBplF2UKE0AAU0AAWWMAnZmlF2UKE0AAU0AAWV1YXUu",
|
25 |
+
"log_std_init": -1,
|
26 |
+
"ortho_init": false,
|
27 |
+
"activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
|
28 |
+
"net_arch": [
|
29 |
+
{
|
30 |
+
"pi": [
|
31 |
+
256,
|
32 |
+
256
|
33 |
+
],
|
34 |
+
"vf": [
|
35 |
+
256,
|
36 |
+
256
|
37 |
+
]
|
38 |
+
}
|
39 |
+
]
|
40 |
+
},
|
41 |
+
"observation_space": {
|
42 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
43 |
+
":serialized:": "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",
|
44 |
+
"dtype": "float32",
|
45 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n 0.]",
|
46 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf 1.]",
|
47 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False True]",
|
48 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False True]",
|
49 |
+
"_np_random": null,
|
50 |
+
"_shape": [
|
51 |
+
29
|
52 |
+
]
|
53 |
+
},
|
54 |
+
"action_space": {
|
55 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
56 |
+
":serialized:": "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",
|
57 |
+
"dtype": "float32",
|
58 |
+
"low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
|
59 |
+
"high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
|
60 |
+
"bounded_below": "[ True True True True True True True True]",
|
61 |
+
"bounded_above": "[ True True True True True True True True]",
|
62 |
+
"_np_random": "RandomState(MT19937)",
|
63 |
+
"_shape": [
|
64 |
+
8
|
65 |
+
]
|
66 |
+
},
|
67 |
+
"n_envs": 16,
|
68 |
+
"num_timesteps": 2007040,
|
69 |
+
"_total_timesteps": 2000000,
|
70 |
+
"_num_timesteps_at_start": 0,
|
71 |
+
"seed": 0,
|
72 |
+
"action_noise": null,
|
73 |
+
"start_time": 1614621250.532368,
|
74 |
+
"learning_rate": {
|
75 |
+
":type:": "<class 'function'>",
|
76 |
+
":serialized:": "gASV2QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxVL3ZvbHVtZS9VU0VSU1RPUkUvcmFmZl9hbi9wcm9qZWN0cy90b3JjaHktYmFzZWxpbmVzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS3xDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVS92b2x1bWUvVVNFUlNUT1JFL3JhZmZfYW4vcHJvamVjdHMvdG9yY2h5LWJhc2VsaW5lcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPv91EE1VHWmFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
77 |
+
},
|
78 |
+
"tensorboard_log": null,
|
79 |
+
"lr_schedule": {
|
80 |
+
":type:": "<class 'function'>",
|
81 |
+
":serialized:": "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"
|
82 |
+
},
|
83 |
+
"_last_obs": null,
|
84 |
+
"_last_episode_starts": null,
|
85 |
+
"_last_original_obs": {
|
86 |
+
":type:": "<class 'numpy.ndarray'>",
|
87 |
+
":serialized:": "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"
|
88 |
+
},
|
89 |
+
"_episode_num": 0,
|
90 |
+
"use_sde": true,
|
91 |
+
"sde_sample_freq": 4,
|
92 |
+
"_current_progress_remaining": -0.0035199999999999676,
|
93 |
+
"ep_info_buffer": {
|
94 |
+
":type:": "<class 'collections.deque'>",
|
95 |
+
":serialized:": "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"
|
96 |
+
},
|
97 |
+
"ep_success_buffer": {
|
98 |
+
":type:": "<class 'collections.deque'>",
|
99 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
100 |
+
},
|
101 |
+
"_n_updates": 4900,
|
102 |
+
"n_steps": 512,
|
103 |
+
"gamma": 0.99,
|
104 |
+
"gae_lambda": 0.9,
|
105 |
+
"ent_coef": 0.0,
|
106 |
+
"vf_coef": 0.5,
|
107 |
+
"max_grad_norm": 0.5,
|
108 |
+
"batch_size": 128,
|
109 |
+
"n_epochs": 20,
|
110 |
+
"clip_range": {
|
111 |
+
":type:": "<class 'function'>",
|
112 |
+
":serialized:": "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"
|
113 |
+
},
|
114 |
+
"clip_range_vf": null,
|
115 |
+
"normalize_advantage": true,
|
116 |
+
"target_kl": null,
|
117 |
+
"_last_dones": {
|
118 |
+
":type:": "<class 'numpy.ndarray'>",
|
119 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
120 |
+
}
|
121 |
+
}
|
ppo-AntBulletEnv-v0/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79ce42aff824ac38e1a2facacade4ef8f150027c2822562f38bf7541847175d4
|
3 |
+
size 1217431
|
ppo-AntBulletEnv-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b824cb6a294ba405a8e6bb60c365d96a85c302d67236607897715119cb7e4ba
|
3 |
+
size 609534
|
ppo-AntBulletEnv-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-AntBulletEnv-v0/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
|
2 |
+
Python: 3.7.10
|
3 |
+
Stable-Baselines3: 1.5.1a8
|
4 |
+
PyTorch: 1.11.0
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.2
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15769e2018c1789f1b8f40e2bc5be0542fba90bb8b833438ef0998dcb9e776da
|
3 |
+
size 1234795
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 2878.4037468999995, "std_reward": 58.19849739036336, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:53:44.728043"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ef9f96e9686fb67c38e7475f9e4024e5d4757f56b7e2dcdf40b5db5bd58054b
|
3 |
+
size 97705
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c97c0c80e61301df7aa8790d819b741a4a07780be53d4d7c152688d09d0f4bcc
|
3 |
+
size 6986
|