Upload PPO LunarLander-v2 trained agent
Browse files- README.md +4 -19
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +22 -22
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +2 -2
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
@@ -26,27 +26,12 @@ This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
|
|
29 |
|
30 |
|
31 |
```python
|
32 |
-
|
33 |
-
import gymnasium as gym
|
34 |
-
|
35 |
from huggingface_sb3 import load_from_hub
|
36 |
|
37 |
-
|
38 |
-
from stable_baselines3.common.evaluation import evaluate_policy
|
39 |
-
from stable_baselines3.common.monitor import Monitor
|
40 |
-
|
41 |
-
repo_id = "AdanLee/ppo-LunarLander-v2"
|
42 |
-
filename = "ppo-LunarLander-v2.zip"
|
43 |
-
|
44 |
-
custom_objects = {
|
45 |
-
"learning_rate": 0.0,
|
46 |
-
"lr_schedule": lambda _: 0.0,
|
47 |
-
"clip_range": lambda _: 0.0,
|
48 |
-
}
|
49 |
-
|
50 |
-
checkpoint = load_from_hub(repo_id, filename)
|
51 |
-
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)
|
52 |
```
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 287.42 +/- 19.54
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
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
CHANGED
@@ -1 +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 0x78ed006d0280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78ed006d0310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78ed006d03a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78ed006d0430>", "_build": "<function ActorCriticPolicy._build at 0x78ed006d04c0>", "forward": "<function ActorCriticPolicy.forward at 0x78ed006d0550>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78ed006d05e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78ed006d0670>", "_predict": "<function ActorCriticPolicy._predict at 0x78ed006d0700>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78ed006d0790>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78ed006d0820>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78ed006d08b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78ed006c3540>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689303633159207530, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.31 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 0x7e1b4abf5ab0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e1b4abf5b40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e1b4abf5bd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e1b4abf5c60>", "_build": "<function ActorCriticPolicy._build at 0x7e1b4abf5cf0>", "forward": "<function ActorCriticPolicy.forward at 0x7e1b4abf5d80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e1b4abf5e10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e1b4abf5ea0>", "_predict": "<function ActorCriticPolicy._predict at 0x7e1b4abf5f30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e1b4abf5fc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e1b4abf6050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e1b4abf60e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e1b4ab9b140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693453722322745580, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_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": 1230, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.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 sha256:2c6aee61b55dc66110bb996b60758dc26c60d5215e61bfdb6b17582191ee015c
|
3 |
+
size 146629
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
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._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,17 +41,17 @@
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -83,8 +83,8 @@
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
|
|
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 0x7e1b4abf5ab0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e1b4abf5b40>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e1b4abf5bd0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e1b4abf5c60>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7e1b4abf5cf0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7e1b4abf5d80>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7e1b4abf5e10>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e1b4abf5ea0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7e1b4abf5f30>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e1b4abf5fc0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e1b4abf6050>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7e1b4abf60e0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7e1b4ab9b140>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 2015232,
|
25 |
+
"_total_timesteps": 2000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1693453722322745580,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.007616000000000067,
|
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": 1230,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 128,
|
87 |
+
"n_epochs": 10,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a648f809b3d3ddab7455e52a25b6e0ac63b6953e6fad24da04c6fd97b16ebaea
|
3 |
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43329
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd72ae446d8e14b7a9bcecb39e0d7ee1b961b3dc9992455f89e70b0d74831131
|
3 |
size 43329
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
-
- OS: Linux-5.15.109+-x86_64-with-glibc2.
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
- PyTorch: 2.0.1+cu118
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
- PyTorch: 2.0.1+cu118
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 287.41761099999997, "std_reward": 19.544318536078233, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-31T04:20:36.199709"}
|