Iamvincent
commited on
Commit
•
90885fd
1
Parent(s):
24a59c6
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +16 -40
- config.json +1 -1
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +95 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- LunarLander-v2
|
4 |
-
- ppo
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
-
-
|
8 |
-
- deep-rl-course
|
9 |
model-index:
|
10 |
- name: PPO
|
11 |
results:
|
@@ -17,45 +16,22 @@ model-index:
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
-
value:
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
24 |
|
25 |
-
|
|
|
|
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
'wandb_entity': None
|
38 |
-
'capture_video': False
|
39 |
-
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps': 500000
|
41 |
-
'learning_rate': 0.00025
|
42 |
-
'num_envs': 16
|
43 |
-
'num_steps': 128
|
44 |
-
'anneal_lr': True
|
45 |
-
'gae': True
|
46 |
-
'gamma': 0.99
|
47 |
-
'gae_lambda': 0.95
|
48 |
-
'num_minibatches': 4
|
49 |
-
'update_epochs': 4
|
50 |
-
'norm_adv': True
|
51 |
-
'clip_coef': 0.1
|
52 |
-
'clip_vloss': True
|
53 |
-
'ent_coef': 0.01
|
54 |
-
'vf_coef': 0.5
|
55 |
-
'max_grad_norm': 0.5
|
56 |
-
'target_kl': None
|
57 |
-
'repo_id': 'Iamvincent/ppo-LunarLander-v2'
|
58 |
-
'batch_size': 2048
|
59 |
-
'minibatch_size': 512}
|
60 |
-
```
|
61 |
-
|
|
|
1 |
---
|
2 |
+
library_name: stable-baselines3
|
3 |
tags:
|
4 |
- LunarLander-v2
|
|
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
|
|
8 |
model-index:
|
9 |
- name: PPO
|
10 |
results:
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 253.81 +/- 13.14
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
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 |
+
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 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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f85ca402820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f85ca4028b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f85ca402940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f85ca4029d0>", "_build": "<function ActorCriticPolicy._build at 0x7f85ca402a60>", "forward": "<function ActorCriticPolicy.forward at 0x7f85ca402af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f85ca402b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f85ca402c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f85ca402ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f85ca402d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f85ca402dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f85ca400690>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670445586886204700, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
|
|
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 0x7efcfe88e9d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efcfe88ea60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efcfe88eaf0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efcfe88eb80>", "_build": "<function ActorCriticPolicy._build at 0x7efcfe88ec10>", "forward": "<function ActorCriticPolicy.forward at 0x7efcfe88eca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efcfe88ed30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efcfe88edc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7efcfe88ee50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efcfe88eee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efcfe88ef70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efcfe891040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7efcfe8876c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677606902854704843, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e44135333daac3fca176169cfb7ea552e31ff0675359f8597d18d7cab80f73c
|
3 |
+
size 147420
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7efcfe88e9d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efcfe88ea60>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efcfe88eaf0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efcfe88eb80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7efcfe88ec10>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7efcfe88eca0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7efcfe88ed30>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efcfe88edc0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7efcfe88ee50>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efcfe88eee0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efcfe88ef70>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7efcfe891040>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7efcfe8876c0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
+
"dtype": "float32",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1677606902854704843,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 248,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null
|
95 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:169da342622d4748c93b37e264317c50bd924e5105b7d273e5b132d0a2c67e63
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74356cdc0ae963b2c453bee03d766981ba94930146be10d623cdd9b6fa4463bb
|
3 |
+
size 43393
|
ppo-LunarLander-v2/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-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"mean_reward": 253.80852217988257, "std_reward": 13.141150536281588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T18:17:29.655372"}
|