markeidsaune
commited on
Commit
•
d9a55a9
1
Parent(s):
c93d749
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +15 -8
- config.json +1 -1
- ppo-LunarLander-v2.zip +1 -1
- ppo-LunarLander-v2/data +16 -16
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +1 -1
- 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:
|
@@ -17,14 +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 |
-
|
|
|
|
|
|
|
|
|
|
|
|
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: 259.30 +/- 24.14
|
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 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 0x7f82c65d2790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f82c65d2820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f82c65d28b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f82c65d2940>", "_build": "<function ActorCriticPolicy._build at 0x7f82c65d29d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f82c65d2a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f82c65d2af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f82c65d2b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f82c65d2c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f82c65d2ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f82c65d2d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f82c65d2dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f82c65caa20>"}, "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": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680800758668207288, "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-5.15.0-56-generic-x86_64-with-glibc2.29 # 62~20.04.1-Ubuntu SMP Tue Nov 22 21:24:20 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "2.0.0+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "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 0x7f5f3b14a700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5f3b14a790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5f3b14a820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5f3b14a8b0>", "_build": "<function ActorCriticPolicy._build at 0x7f5f3b14a940>", "forward": "<function ActorCriticPolicy.forward at 0x7f5f3b14a9d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5f3b14aa60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5f3b14aaf0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5f3b14ab80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5f3b14ac10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5f3b14aca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5f3b14ad30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5f3b146780>"}, "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": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1684951338260018437, "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-5.15.0-69-generic-x86_64-with-glibc2.29 # 76~20.04.1-Ubuntu SMP Mon Mar 20 15:54:19 UTC 2023", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "2.0.0+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 147557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d78cd828e12f8f723191df3d3f75a8797676d166793b41e7f56e762298abc4f
|
3 |
size 147557
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -48,7 +48,7 @@
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -70,7 +70,7 @@
|
|
70 |
"_current_progress_remaining": -0.015808000000000044,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
|
|
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 0x7f5f3b14a700>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5f3b14a790>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5f3b14a820>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5f3b14a8b0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f5f3b14a940>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f5f3b14a9d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5f3b14aa60>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5f3b14aaf0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f5f3b14ab80>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5f3b14ac10>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5f3b14aca0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5f3b14ad30>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f5f3b146780>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1684951338260018437,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
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'>",
|
|
|
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'>",
|
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 sha256:42058af59706119d223fb11c4710375abf0505f6104a3326c21ceaf04db7db9b
|
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 43393
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff891556b8fa1b8c43bfcdf4e1cb324671bd66a29c3e24eabbdbede1395e52aa
|
3 |
size 43393
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
- OS: Linux-5.15.0-
|
2 |
- Python: 3.8.10
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
- PyTorch: 2.0.0+cu117
|
|
|
1 |
+
- OS: Linux-5.15.0-69-generic-x86_64-with-glibc2.29 # 76~20.04.1-Ubuntu SMP Mon Mar 20 15:54:19 UTC 2023
|
2 |
- Python: 3.8.10
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
- PyTorch: 2.0.0+cu117
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"mean_reward": 259.3006601930232, "std_reward": 24.14170217785775, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-24T14:23:38.901535"}
|