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-Walker2DBulletEnv-v0.zip +3 -0
- ppo-Walker2DBulletEnv-v0/_stable_baselines3_version +1 -0
- ppo-Walker2DBulletEnv-v0/data +121 -0
- ppo-Walker2DBulletEnv-v0/policy.optimizer.pth +3 -0
- ppo-Walker2DBulletEnv-v0/policy.pth +3 -0
- ppo-Walker2DBulletEnv-v0/pytorch_variables.pth +3 -0
- ppo-Walker2DBulletEnv-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 |
+
- Walker2DBulletEnv-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: 2120.20 +/- 6.34
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: Walker2DBulletEnv-v0
|
20 |
+
type: Walker2DBulletEnv-v0
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **Walker2DBulletEnv-v0**
|
24 |
+
This is a trained model of a **PPO** agent playing **Walker2DBulletEnv-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 Walker2DBulletEnv-v0 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo ppo --env Walker2DBulletEnv-v0 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo ppo --env Walker2DBulletEnv-v0 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo ppo --env Walker2DBulletEnv-v0 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('batch_size', 128),
|
54 |
+
('clip_range', 'lin_0.4'),
|
55 |
+
('ent_coef', 0.0),
|
56 |
+
('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
|
57 |
+
('gae_lambda', 0.92),
|
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=-2, 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 |
+
- Walker2DBulletEnv-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 |
+
- 4258832375
|
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 |
+
- lin_0.4
|
6 |
+
- - ent_coef
|
7 |
+
- 0.0
|
8 |
+
- - env_wrapper
|
9 |
+
- sb3_contrib.common.wrappers.TimeFeatureWrapper
|
10 |
+
- - gae_lambda
|
11 |
+
- 0.92
|
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=-2, 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-Walker2DBulletEnv-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6af5caea6ad924381142e58dd9d0587f042a73a6b8f288f44d6b9e7360e9991
|
3 |
+
size 1800681
|
ppo-Walker2DBulletEnv-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
ppo-Walker2DBulletEnv-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 0x7f96d85d7950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f96d85d79e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f96d85d7a70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f96d85d7b00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f96d85d7b90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f96d85d7c20>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f96d85d7cb0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f96d85d7d40>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f96d85d7dd0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f96d85d7e60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f96d85d7ef0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f96d8629840>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {
|
23 |
+
":type:": "<class 'dict'>",
|
24 |
+
":serialized:": "gASVjgAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA1hY3RpdmF0aW9uX2ZulIwbdG9yY2gubm4ubW9kdWxlcy5hY3RpdmF0aW9ulIwEUmVMVZSTlIwIbmV0X2FyY2iUXZR9lCiMAnBplF2UKE0AAU0AAWWMAnZmlF2UKE0AAU0AAWV1YXUu",
|
25 |
+
"log_std_init": -2,
|
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 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 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 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 True]",
|
49 |
+
"_np_random": null,
|
50 |
+
"_shape": [
|
51 |
+
23
|
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.]",
|
59 |
+
"high": "[1. 1. 1. 1. 1. 1.]",
|
60 |
+
"bounded_below": "[ True True True True True True]",
|
61 |
+
"bounded_above": "[ True True True True True True]",
|
62 |
+
"_np_random": "RandomState(MT19937)",
|
63 |
+
"_shape": [
|
64 |
+
6
|
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": 1614621250.5323632,
|
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": 0.92,
|
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-Walker2DBulletEnv-v0/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0031b94c0f03f8647740b6eebe12ee6dd3e0dae72a156765b84b7faf563f9dab
|
3 |
+
size 1184663
|
ppo-Walker2DBulletEnv-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe892215a83f99c4b3607101c9b80c8c797fb6d9627889ed6c7dfa92be259674
|
3 |
+
size 593150
|
ppo-Walker2DBulletEnv-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-Walker2DBulletEnv-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 sha256:4a3aca6f30b599e5551c19de9a7223fd47d02e974181092cc9e0b0c5edd4ce95
|
3 |
+
size 1103932
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 2120.196074, "std_reward": 6.344277244758598, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T14:57:38.456770"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7482c5b9340a7a5f7f961ed69aea011ef68a7fce5aec10ec6b44b8dc935b5b8
|
3 |
+
size 245111
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44fb5e7991a81f5e12634c4244fc9a04cb56ad44f3e9d41d79a2db3374cd970f
|
3 |
+
size 6426
|