first
Browse files- README.md +37 -0
- config.json +1 -0
- 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 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 243.25 +/- 21.13
|
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
ADDED
@@ -0,0 +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 0x7f9538cd7670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9538cd7700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9538cd7790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9538cd7820>", "_build": "<function ActorCriticPolicy._build at 0x7f9538cd78b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f9538cd7940>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9538cd79d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9538cd7a60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9538cd7af0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9538cd7b80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9538cd7c10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9538cd7ca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9538cd9140>"}, "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": 1680432699063440952, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "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 sha256:51bdf6e8e811906911cdde4c7e350dbc6d07c253f1cf80d4279012b5324c67cf
|
3 |
+
size 147425
|
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 0x7f9538cd7670>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9538cd7700>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9538cd7790>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9538cd7820>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9538cd78b0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9538cd7940>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9538cd79d0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9538cd7a60>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9538cd7af0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9538cd7b80>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9538cd7c10>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9538cd7ca0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f9538cd9140>"
|
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": 1680432699063440952,
|
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:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAM0W4rz2dGe6KH6AuTl1m7QNj6C6ll2VOAAAgD8AAIA/AMzPvRRagLr+anM7Kx/ytidC8rpFJxO6AACAPwAAgD8a8To9XAdTupBVkLtSCpk4o0r3OkI1vjkAAIA/AACAP2aGuzvhhoW6jkXnOuaX0TXbfig7lrsGugAAgD8AAIA/gMEbPUhdkLqHppO6vNcmtQ/o57qhaqo5AACAPwAAgD/NLXC9hTv9uWwOqjZsXDIyZfK6O38Fy7UAAIA/AACAP80afzyPlny6+PJcu92MIzgYrAW6VUsDOgAAgD8AAIA/6iBavmQemz+KKiu/iSwvvwfGgL4T3k2+AAAAAAAAAAAz87q8j4YjuksD5DpehDw1w1SRu1ZqB7oAAIA/AACAP5qM7jyP0mS6CDnlOvyBMjXeoSq7ZkUGugAAgD8AAIA/Zqa6usNJH7p2No641TClsyjzXztFqKU3AACAPwAAgD8z+pG89jg0usg657umXrQ403Afu6LWazkAAIA/AACAPwBX/DwFuoa7+YyKPPL1gjxn+aS8Y71dPQAAgD8AAIA/mgWsvMNZdbphtK+6pNOstRg8VzsSPM05AACAPwAAgD9aPu+9fx8pPz12ULwzna6+oCaZvQlUqj0AAAAAAAAAAJq0ijxpISW8xkTwOqeM2TySeoW9Kt+wPQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
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:a067a7cd70927e5be4df14a6ed247a8f1ad72cd1f6d05f2a8fda75a8129a2c98
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:850be426d70cbed2f7da03f1f30196f44d8e1922c6cc859cc857cbfd6bc5eb8d
|
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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.9.16
|
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
ADDED
Binary file (227 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 243.2465196491816, "std_reward": 21.127172497363837, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-02T11:25:28.445111"}
|