harryb0905
commited on
Commit
•
3bb5e79
1
Parent(s):
3b1e232
Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- lunar_lander_ppo_1_million.zip +3 -0
- lunar_lander_ppo_1_million/_stable_baselines3_version +1 -0
- lunar_lander_ppo_1_million/data +94 -0
- lunar_lander_ppo_1_million/policy.optimizer.pth +3 -0
- lunar_lander_ppo_1_million/policy.pth +3 -0
- lunar_lander_ppo_1_million/pytorch_variables.pth +3 -0
- lunar_lander_ppo_1_million/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 265.29 +/- 18.29
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f4360149440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f43601494d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4360149560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f43601495f0>", "_build": "<function ActorCriticPolicy._build at 0x7f4360149680>", "forward": "<function ActorCriticPolicy.forward at 0x7f4360149710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f43601497a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4360149830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f43601498c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4360149950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f43601499e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f4360116960>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROdWIu", "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////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": 1653849412.3499296, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
lunar_lander_ppo_1_million.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f52ddf79d96dd24f8cf0bc1559de8ce46b0eb187e203ecb76435bff59280dedb
|
3 |
+
size 144130
|
lunar_lander_ppo_1_million/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
lunar_lander_ppo_1_million/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f4360149440>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f43601494d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4360149560>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f43601495f0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f4360149680>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f4360149710>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f43601497a0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f4360149830>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f43601498c0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4360149950>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f43601499e0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f4360116960>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653849412.3499296,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 248,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
lunar_lander_ppo_1_million/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:380aa0f5a9d5b29f43cabd0b4cd66788496a6c1739ccd8d2a2b34ffd2791ce28
|
3 |
+
size 84829
|
lunar_lander_ppo_1_million/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:998df6378c6ff9682e8090d2caf91e53f3b8a45d66346bd269b0073f20df2b48
|
3 |
+
size 43201
|
lunar_lander_ppo_1_million/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
lunar_lander_ppo_1_million/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e7a86b2ba50c77b7b99a83f955c905765f77df5d862407e54cee429f865847
|
3 |
+
size 239971
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 265.2899521586516, "std_reward": 18.285358969278043, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-29T19:23:51.482906"}
|