Upload PPO CartPole-v1 trained agent
Browse files- README.md +37 -37
- config.json +1 -1
- ppo-CartPole-v1.zip +2 -2
- ppo-CartPole-v1/data +41 -29
- ppo-CartPole-v1/policy.optimizer.pth +2 -2
- ppo-CartPole-v1/policy.pth +1 -1
- results.json +1 -1
README.md
CHANGED
@@ -1,37 +1,37 @@
|
|
1 |
-
---
|
2 |
-
library_name: stable-baselines3
|
3 |
-
tags:
|
4 |
-
-
|
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:
|
16 |
-
type:
|
17 |
-
metrics:
|
18 |
-
- type: mean_reward
|
19 |
-
value:
|
20 |
-
name: mean_reward
|
21 |
-
verified: false
|
22 |
-
---
|
23 |
-
|
24 |
-
# **PPO** Agent playing **
|
25 |
-
This is a trained model of a **PPO** agent playing **
|
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 |
-
```
|
|
|
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: 489.50 +/- 31.50
|
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
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 0x7e5efafc0c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e5efafc0ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e5efafc0d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e5efafc0dc0>", "_build": "<function ActorCriticPolicy._build at 0x7e5efafc0e50>", "forward": "<function ActorCriticPolicy.forward at 0x7e5efafc0ee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e5efafc0f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e5efafc1000>", "_predict": "<function ActorCriticPolicy._predict at 0x7e5efafc1090>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e5efafc1120>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e5efafc11b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e5efafc1240>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e5efb153c40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718282393222896864, "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": 252, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x0000028AFBDFB060>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000028AFBDFB100>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000028AFBDFB1A0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000028AFBDFB240>", "_build": "<function ActorCriticPolicy._build at 0x0000028AFBDFB2E0>", "forward": "<function ActorCriticPolicy.forward at 0x0000028AFBDFB380>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000028AFBDFB420>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000028AFBDFB4C0>", "_predict": "<function ActorCriticPolicy._predict at 0x0000028AFBDFB560>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000028AFBDFB600>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000028AFBDFB6A0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000028AFBDFB740>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000028AFBDFE240>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718287776266033800, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAADod8bzdxTI/YbhyvazeFr2UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.0035199999999999676, "_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": 392, "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": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function RolloutBuffer.__init__ at 0x0000028AFBB2AC00>", "reset": "<function RolloutBuffer.reset at 0x0000028AFBB2ACA0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x0000028AFBB2AD40>", "add": "<function RolloutBuffer.add at 0x0000028AFBB2AE80>", "get": "<function RolloutBuffer.get at 0x0000028AFBB2AF20>", "_get_samples": "<function RolloutBuffer._get_samples at 0x0000028AFBB2AFC0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000028AFBB23B80>"}, "rollout_buffer_kwargs": {}, "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": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.11.9", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
|
ppo-CartPole-v1.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 sha256:6a44e886285163a0bd10e79d8fedaf9bfa9972ac539b112a6c943bc8ab46f673
|
3 |
+
size 142219
|
ppo-CartPole-v1/data
CHANGED
@@ -4,42 +4,54 @@
|
|
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 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
"_last_original_obs": null,
|
35 |
"_episode_num": 0,
|
36 |
"use_sde": false,
|
37 |
"sde_sample_freq": -1,
|
38 |
-
"_current_progress_remaining":
|
39 |
"_stats_window_size": 100,
|
40 |
-
"ep_info_buffer":
|
41 |
-
|
42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
"observation_space": {
|
44 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
45 |
":serialized:": "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",
|
@@ -77,14 +89,14 @@
|
|
77 |
"__module__": "stable_baselines3.common.buffers",
|
78 |
"__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
|
79 |
"__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
|
80 |
-
"__init__": "<function RolloutBuffer.__init__ at
|
81 |
-
"reset": "<function RolloutBuffer.reset at
|
82 |
-
"compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at
|
83 |
-
"add": "<function RolloutBuffer.add at
|
84 |
-
"get": "<function RolloutBuffer.get at
|
85 |
-
"_get_samples": "<function RolloutBuffer._get_samples at
|
86 |
"__abstractmethods__": "frozenset()",
|
87 |
-
"_abc_impl": "<_abc._abc_data object at
|
88 |
},
|
89 |
"rollout_buffer_kwargs": {},
|
90 |
"batch_size": 64,
|
|
|
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 0x0000028AFBDFB060>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000028AFBDFB100>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000028AFBDFB1A0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000028AFBDFB240>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x0000028AFBDFB2E0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x0000028AFBDFB380>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x0000028AFBDFB420>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000028AFBDFB4C0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x0000028AFBDFB560>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000028AFBDFB600>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000028AFBDFB6A0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x0000028AFBDFB740>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x0000028AFBDFE240>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 100352,
|
25 |
+
"_total_timesteps": 100000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1718287776266033800,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAADod8bzdxTI/YbhyvazeFr2UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.0035199999999999676,
|
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": 392,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
89 |
"__module__": "stable_baselines3.common.buffers",
|
90 |
"__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
|
91 |
"__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
|
92 |
+
"__init__": "<function RolloutBuffer.__init__ at 0x0000028AFBB2AC00>",
|
93 |
+
"reset": "<function RolloutBuffer.reset at 0x0000028AFBB2ACA0>",
|
94 |
+
"compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x0000028AFBB2AD40>",
|
95 |
+
"add": "<function RolloutBuffer.add at 0x0000028AFBB2AE80>",
|
96 |
+
"get": "<function RolloutBuffer.get at 0x0000028AFBB2AF20>",
|
97 |
+
"_get_samples": "<function RolloutBuffer._get_samples at 0x0000028AFBB2AFC0>",
|
98 |
"__abstractmethods__": "frozenset()",
|
99 |
+
"_abc_impl": "<_abc._abc_data object at 0x0000028AFBB23B80>"
|
100 |
},
|
101 |
"rollout_buffer_kwargs": {},
|
102 |
"batch_size": 64,
|
ppo-CartPole-v1/policy.optimizer.pth
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 sha256:349547446730bc33b3f868b2ba058686685288865769101e846b48a40239444d
|
3 |
+
size 83242
|
ppo-CartPole-v1/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41202
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fcf60597aa05f19c831ff25b3190f0aa76d0da2c817f65508bca9ad93dd25db
|
3 |
size 41202
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 489.5, "std_reward": 31.5, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-13T17:11:41.915744"}
|