Upload best PPO LunarLander-v2 agent (tuned with Optuna).
Browse files- PPO-LunarLander-v2.zip +3 -0
- PPO-LunarLander-v2/_stable_baselines3_version +1 -0
- PPO-LunarLander-v2/data +94 -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
- README.md +36 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3603744e302013458e36d08647ba2434876be165298e31e6194a38d078bfd311
|
3 |
+
size 147075
|
PPO-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
PPO-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 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 0x7f7364aa5b80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7364aa5c10>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7364aa5ca0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7364aa5d30>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f7364aa5dc0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f7364aa5e50>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7364aa5ee0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f7364aa5f70>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7364a2b040>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7364a2b0d0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7364a2b160>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f7364a2a840>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
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:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1851392,
|
46 |
+
"_total_timesteps": 1840911,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1657580656.2181077,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gAWV2wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFUvaG9tZS9hdXRvd2luL2FuYWNvbmRhMy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxVL2hvbWUvYXV0b3dpbi9hbmFjb25kYTMvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoF2gOjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGIwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.005693376811806816,
|
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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 452,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.9918578409032625,
|
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:": "gAWV2wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFUvaG9tZS9hdXRvd2luL2FuYWNvbmRhMy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxVL2hvbWUvYXV0b3dpbi9hbmFjb25kYTMvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoF2gOjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGIwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
PPO-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d029a45b2c08cc2a7d004104287601646b9456bd6034f0883416e7e7a83483fe
|
3 |
+
size 87865
|
PPO-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94261076bd03150c6a4c0e587f63b4964e0428572e5066e240813cdc13a41b86
|
3 |
+
size 43201
|
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-5.15.0-40-generic-x86_64-with-glibc2.35 #43-Ubuntu SMP Wed Jun 15 12:54:21 UTC 2022
|
2 |
+
Python: 3.9.12
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.12.0+cu102
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.5
|
7 |
+
Gym: 0.21.0
|
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: 282.46 +/- 19.55
|
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:": "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 0x7f7364aa5b80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7364aa5c10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7364aa5ca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7364aa5d30>", "_build": "<function ActorCriticPolicy._build at 0x7f7364aa5dc0>", "forward": "<function ActorCriticPolicy.forward at 0x7f7364aa5e50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7364aa5ee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7364aa5f70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7364a2b040>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7364a2b0d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7364a2b160>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f7364a2a840>"}, "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": 1851392, "_total_timesteps": 1840911, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657580656.2181077, "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": -0.005693376811806816, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 452, "n_steps": 1024, "gamma": 0.9918578409032625, "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-5.15.0-40-generic-x86_64-with-glibc2.35 #43-Ubuntu SMP Wed Jun 15 12:54:21 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.21.5", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (224 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 282.45668832497824, "std_reward": 19.549892926397302, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-12T00:45:11.904791"}
|