Commit
•
e735b38
1
Parent(s):
1cad489
Push to Hub
Browse files- PPO-CartPole-v1.zip +3 -0
- PPO-CartPole-v1/_stable_baselines3_version +1 -0
- PPO-CartPole-v1/data +99 -0
- PPO-CartPole-v1/policy.optimizer.pth +3 -0
- PPO-CartPole-v1/policy.pth +3 -0
- PPO-CartPole-v1/pytorch_variables.pth +3 -0
- PPO-CartPole-v1/system_info.txt +9 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO-CartPole-v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75021282481127d4a651b6ba1d6cbaaea002656f84bba6a29245d033cdd283e8
|
3 |
+
size 139076
|
PPO-CartPole-v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.1.0
|
PPO-CartPole-v1/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x32280f940>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x32280f9d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x32280fa60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x32280faf0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x32280fb80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x32280fc10>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x32280fca0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x32280fd30>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x32280fdc0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x32280fe50>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x32280fee0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x32280ff70>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x322811c40>"
|
21 |
+
},
|
22 |
+
"verbose": 0,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 30720,
|
25 |
+
"_total_timesteps": 30000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1713092649050547000,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAE0y1L8c7Bw/EqUzPYOdB7+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
|
35 |
+
},
|
36 |
+
"_last_episode_starts": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.02400000000000002,
|
45 |
+
"_stats_window_size": 100,
|
46 |
+
"ep_info_buffer": {
|
47 |
+
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 150,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True]",
|
60 |
+
"bounded_above": "[ True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
4
|
63 |
+
],
|
64 |
+
"low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
|
65 |
+
"high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
|
66 |
+
"low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
|
67 |
+
"high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "2",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 1,
|
80 |
+
"n_steps": 2048,
|
81 |
+
"gamma": 0.99,
|
82 |
+
"gae_lambda": 0.95,
|
83 |
+
"ent_coef": 0.0,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "gAWVIgMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMhi9Vc2Vycy9zdWJoYXNpc2gvRG9jdW1lbnRzL2lOZXVyb24vUmVpbmZvcmNlbWVudC1MZWFybmluZy9kcmwtMmVkL3JsX2RybC9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIyGL1VzZXJzL3N1Ymhhc2lzaC9Eb2N1bWVudHMvaU5ldXJvbi9SZWluZm9yY2VtZW50LUxlYXJuaW5nL2RybC0yZWQvcmxfZHJsL2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
+
}
|
PPO-CartPole-v1/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4583610b86bfa422fd45f96644be8d0cd425445d6e7dae4697d3a3b33c65d17d
|
3 |
+
size 82858
|
PPO-CartPole-v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9101a38ed41b608a7c17db939bf2594a10053f0e87e619f480c81ce27a6a266
|
3 |
+
size 41074
|
PPO-CartPole-v1/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
|
3 |
+
size 864
|
PPO-CartPole-v1/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:12:41 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T8103
|
2 |
+
- Python: 3.9.19
|
3 |
+
- Stable-Baselines3: 2.1.0
|
4 |
+
- PyTorch: 2.2.1
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.26.4
|
7 |
+
- Cloudpickle: 3.0.0
|
8 |
+
- Gymnasium: 0.29.1
|
9 |
+
- OpenAI Gym: 0.26.2
|
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- CartPole-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: CartPole-v1
|
16 |
+
type: CartPole-v1
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 479.40 +/- 29.14
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **CartPole-v1**
|
25 |
+
This is a trained model of a **PPO** agent playing **CartPole-v1**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x32280f940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x32280f9d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x32280fa60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x32280faf0>", "_build": "<function ActorCriticPolicy._build at 0x32280fb80>", "forward": "<function ActorCriticPolicy.forward at 0x32280fc10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x32280fca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x32280fd30>", "_predict": "<function ActorCriticPolicy._predict at 0x32280fdc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x32280fe50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x32280fee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x32280ff70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x322811c40>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 30720, "_total_timesteps": 30000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713092649050547000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAE0y1L8c7Bw/EqUzPYOdB7+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 150, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVIgMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMhi9Vc2Vycy9zdWJoYXNpc2gvRG9jdW1lbnRzL2lOZXVyb24vUmVpbmZvcmNlbWVudC1MZWFybmluZy9kcmwtMmVkL3JsX2RybC9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIyGL1VzZXJzL3N1Ymhhc2lzaC9Eb2N1bWVudHMvaU5ldXJvbi9SZWluZm9yY2VtZW50LUxlYXJuaW5nL2RybC0yZWQvcmxfZHJsL2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVIgMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMhi9Vc2Vycy9zdWJoYXNpc2gvRG9jdW1lbnRzL2lOZXVyb24vUmVpbmZvcmNlbWVudC1MZWFybmluZy9kcmwtMmVkL3JsX2RybC9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIyGL1VzZXJzL3N1Ymhhc2lzaC9Eb2N1bWVudHMvaU5ldXJvbi9SZWluZm9yY2VtZW50LUxlYXJuaW5nL2RybC0yZWQvcmxfZHJsL2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:12:41 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T8103", "Python": "3.9.19", "Stable-Baselines3": "2.1.0", "PyTorch": "2.2.1", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}
|
replay.mp4
ADDED
Binary file (60.2 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 479.4, "std_reward": 29.138290958805392, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-14T16:38:49.073516"}
|