first commit
Browse files- LunarLander.zip +3 -0
- LunarLander/_stable_baselines3_version +1 -0
- LunarLander/data +96 -0
- LunarLander/policy.optimizer.pth +3 -0
- LunarLander/policy.pth +3 -0
- LunarLander/pytorch_variables.pth +3 -0
- LunarLander/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
LunarLander.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65d4e18cee6b0bab35471412e84ed6c288d0b8d023e4a87d96c01f18cd6a149d
|
3 |
+
size 147363
|
LunarLander/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0
|
LunarLander/data
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7fcb94aefdc0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcb94aefe50>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcb94aefee0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcb94aeff70>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fcb94af3040>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fcb94af30d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcb94af3160>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcb94af31f0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fcb94af3280>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcb94af3310>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcb94af33a0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcb94af3430>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fcb94af0f40>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1682492870883517270,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"lr_schedule": {
|
33 |
+
":type:": "<class 'function'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_obs": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "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"
|
39 |
+
},
|
40 |
+
"_last_episode_starts": {
|
41 |
+
":type:": "<class 'numpy.ndarray'>",
|
42 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
43 |
+
},
|
44 |
+
"_last_original_obs": null,
|
45 |
+
"_episode_num": 0,
|
46 |
+
"use_sde": false,
|
47 |
+
"sde_sample_freq": -1,
|
48 |
+
"_current_progress_remaining": -0.015808000000000044,
|
49 |
+
"_stats_window_size": 100,
|
50 |
+
"ep_info_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "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"
|
53 |
+
},
|
54 |
+
"ep_success_buffer": {
|
55 |
+
":type:": "<class 'collections.deque'>",
|
56 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
57 |
+
},
|
58 |
+
"_n_updates": 248,
|
59 |
+
"observation_space": {
|
60 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
61 |
+
":serialized:": "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",
|
62 |
+
"dtype": "float32",
|
63 |
+
"_shape": [
|
64 |
+
8
|
65 |
+
],
|
66 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
67 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
68 |
+
"bounded_below": "[False False False False False False False False]",
|
69 |
+
"bounded_above": "[False False False False False False False False]",
|
70 |
+
"_np_random": null
|
71 |
+
},
|
72 |
+
"action_space": {
|
73 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
74 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
75 |
+
"n": 4,
|
76 |
+
"_shape": [],
|
77 |
+
"dtype": "int64",
|
78 |
+
"_np_random": null
|
79 |
+
},
|
80 |
+
"n_envs": 16,
|
81 |
+
"n_steps": 1024,
|
82 |
+
"gamma": 0.999,
|
83 |
+
"gae_lambda": 0.98,
|
84 |
+
"ent_coef": 0.01,
|
85 |
+
"vf_coef": 0.5,
|
86 |
+
"max_grad_norm": 0.5,
|
87 |
+
"batch_size": 64,
|
88 |
+
"n_epochs": 4,
|
89 |
+
"clip_range": {
|
90 |
+
":type:": "<class 'function'>",
|
91 |
+
":serialized:": "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"
|
92 |
+
},
|
93 |
+
"clip_range_vf": null,
|
94 |
+
"normalize_advantage": true,
|
95 |
+
"target_kl": null
|
96 |
+
}
|
LunarLander/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc05cfea814ca3800326c4f191227b939fa4c863366d5a3648a6178f52528376
|
3 |
+
size 87929
|
LunarLander/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1910fd554ec612ce35c6aa74a6902d7360651a314cf7868dd29211c510f251de
|
3 |
+
size 43329
|
LunarLander/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
LunarLander/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: 1.8.0
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
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: 261.34 +/- 11.85
|
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 0x7fcb94aefdc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcb94aefe50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcb94aefee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcb94aeff70>", "_build": "<function ActorCriticPolicy._build at 0x7fcb94af3040>", "forward": "<function ActorCriticPolicy.forward at 0x7fcb94af30d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcb94af3160>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcb94af31f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcb94af3280>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcb94af3310>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcb94af33a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcb94af3430>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fcb94af0f40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682492870883517270, "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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVZxAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIU+xoHOqVckCUhpRSlIwBbJRNKwGMAXSUR0CPGgoR7JGOdX2UKGgGaAloD0MIBf2FHvGyckCUhpRSlGgVTQ0BaBZHQI8a4ZGax5d1fZQoaAZoCWgPQwhPAwZJXxVxQJSGlFKUaBVNJAJoFkdAjxxsPSUkfXV9lChoBmgJaA9DCDMWTWfnjnNAlIaUUpRoFUv+aBZHQI8cnWtlqah1fZQoaAZoCWgPQwiitDf4wn9sQJSGlFKUaBVNDAFoFkdAjxzcgyM1j3V9lChoBmgJaA9DCBgFweNbnnFAlIaUUpRoFU0XAWgWR0CPHipVjqfOdX2UKGgGaAloD0MIi8OZX03HcECUhpRSlGgVTQEBaBZHQI8e7Ra5f+l1fZQoaAZoCWgPQwiphCf0+iNuQJSGlFKUaBVNIQFoFkdAjx/E1l5GBnV9lChoBmgJaA9DCKIOK9zy4HFAlIaUUpRoFU0tAWgWR0CPIZ9c8kledX2UKGgGaAloD0MIk45yMNvecUCUhpRSlGgVS+hoFkdAjyQVTR6WxHV9lChoBmgJaA9DCKryPSMREW9AlIaUUpRoFU0SAWgWR0CPJg90zTF3dX2UKGgGaAloD0MIfLlPjsICcECUhpRSlGgVTSEBaBZHQI8mntx+8Xh1fZQoaAZoCWgPQwiLTwEwXgNyQJSGlFKUaBVNIgFoFkdAjydxKYiPhnV9lChoBmgJaA9DCC5U/rU8c3JAlIaUUpRoFU0aAWgWR0CPJ9BMSK3vdX2UKGgGaAloD0MIhX07iYjobECUhpRSlGgVS/poFkdAjyhRKQJXyXV9lChoBmgJaA9DCLNAu0OKE25AlIaUUpRoFU0mAWgWR0CPKgNT987ZdX2UKGgGaAloD0MITpgwmlUMckCUhpRSlGgVTT0BaBZHQI8q1G0/nnx1fZQoaAZoCWgPQwioVl9dlXVvQJSGlFKUaBVNDAFoFkdAjytf4h2W6nV9lChoBmgJaA9DCMJqLGFtZG5AlIaUUpRoFU0QAWgWR0CPLBY/3WWhdX2UKGgGaAloD0MI26UNh2U7cUCUhpRSlGgVTRsBaBZHQI8sZvkzXSV1fZQoaAZoCWgPQwjpgY/BCiByQJSGlFKUaBVNAAFoFkdAjy6R7zCk43V9lChoBmgJaA9DCP/KSpPSLHBAlIaUUpRoFU1AAWgWR0CPMEvmozeodX2UKGgGaAloD0MI7dYyGY7jcUCUhpRSlGgVTTEBaBZHQI8wW09hZyN1fZQoaAZoCWgPQwgrM6X1t2tyQJSGlFKUaBVNHwFoFkdAjzKGp2ll9XV9lChoBmgJaA9DCB050hmY1HBAlIaUUpRoFUv7aBZHQI8zEQEpy6t1fZQoaAZoCWgPQwgpP6n26clwQJSGlFKUaBVNUwJoFkdAjzSjd56dD3V9lChoBmgJaA9DCF2pZ0EopHBAlIaUUpRoFUv3aBZHQI8009t/Fzd1fZQoaAZoCWgPQwhe91Yk5vFxQJSGlFKUaBVNCQFoFkdAjzhWHLzPKXV9lChoBmgJaA9DCIbJVMGoxHJAlIaUUpRoFU0rAWgWR0CPOM3H7xd6dX2UKGgGaAloD0MIO4veqcAfcECUhpRSlGgVTSoBaBZHQI85mNaQmu11fZQoaAZoCWgPQwjc1hael6BxQJSGlFKUaBVNBAFoFkdAjzm7I91U2nV9lChoBmgJaA9DCENVTKUf8HFAlIaUUpRoFUv1aBZHQI860CxNZeR1fZQoaAZoCWgPQwhehCnKJfpxQJSGlFKUaBVNTAFoFkdAjzvb4rSVnnV9lChoBmgJaA9DCP9aXrmex3FAlIaUUpRoFU0VAWgWR0CPPOZwXIludX2UKGgGaAloD0MIRzgteNHpSkCUhpRSlGgVS9BoFkdAjzz3CsOoYXV9lChoBmgJaA9DCKnZA60AJ3BAlIaUUpRoFU0pAWgWR0CPQGriEQGwdX2UKGgGaAloD0MIV1uxv6yKckCUhpRSlGgVTWMBaBZHQI9AbcsUZel1fZQoaAZoCWgPQwgSiNf1i3hwQJSGlFKUaBVNFgFoFkdAj0Euk1uR93V9lChoBmgJaA9DCG6nrRHB4khAlIaUUpRoFUvSaBZHQI9BlcpsoDx1fZQoaAZoCWgPQwieQq7UM8hvQJSGlFKUaBVL/2gWR0CPQhU2kzoEdX2UKGgGaAloD0MI9iUbDzYvbkCUhpRSlGgVS/loFkdAj0I8n/kvK3V9lChoBmgJaA9DCIgRwqON5mHAlIaUUpRoFUuFaBZHQI9CfbItDlZ1fZQoaAZoCWgPQwjVy+80mWNvQJSGlFKUaBVNBQFoFkdAj0P2lVLi/HV9lChoBmgJaA9DCA4sR8hAbVFAlIaUUpRoFUunaBZHQI9F9EXtSht1fZQoaAZoCWgPQwgNAFXcOI5wQJSGlFKUaBVNFQFoFkdAj0fI1UEPlXV9lChoBmgJaA9DCDZ39L+conJAlIaUUpRoFU0LAWgWR0CPSEv7m+0xdX2UKGgGaAloD0MI6xnCMcujbUCUhpRSlGgVTQoBaBZHQI9IXOD8Lrp1fZQoaAZoCWgPQwjLaOTzygtxQJSGlFKUaBVNMwFoFkdAj27DUVi4KHV9lChoBmgJaA9DCDJZ3H/kf3FAlIaUUpRoFU0XAWgWR0CPcPiPyTY/dX2UKGgGaAloD0MIdlH0wIeMcUCUhpRSlGgVTS4BaBZHQI91hkiD/VB1fZQoaAZoCWgPQwgpWU5C6U5wQJSGlFKUaBVL82gWR0CPdZUAksz3dX2UKGgGaAloD0MIf4l467wZckCUhpRSlGgVS/NoFkdAj3a8k2P1c3V9lChoBmgJaA9DCCwQPSnTGnBAlIaUUpRoFUv/aBZHQI92vkPtlZp1fZQoaAZoCWgPQwj27SQi/L9uQJSGlFKUaBVNAwFoFkdAj3os0P6KtXV9lChoBmgJaA9DCKuTMxR3iE5AlIaUUpRoFUunaBZHQI98koF3Y+V1fZQoaAZoCWgPQwi62or95cJuQJSGlFKUaBVNJQFoFkdAj30nIIWxhXV9lChoBmgJaA9DCAfsavIUUmxAlIaUUpRoFU0vAWgWR0CPfULofSx8dX2UKGgGaAloD0MIaObJNQXlcUCUhpRSlGgVTSUBaBZHQI+Auh9LHuJ1fZQoaAZoCWgPQwheTDPdaz5tQJSGlFKUaBVNAwFoFkdAj4Sfoq0+knV9lChoBmgJaA9DCIoAp3cxKHBAlIaUUpRoFU04AWgWR0CPhUzCUHIIdX2UKGgGaAloD0MIeNLCZZXxb0CUhpRSlGgVTSQBaBZHQI+GB/gBLf11fZQoaAZoCWgPQwjYKyy4HzpyQJSGlFKUaBVL92gWR0CPifvZyuIRdX2UKGgGaAloD0MIc6Hyr2UXc0CUhpRSlGgVTUUBaBZHQI+KwnfEXLx1fZQoaAZoCWgPQwjDtkWZzYlyQJSGlFKUaBVNBQFoFkdAj4r0uL74z3V9lChoBmgJaA9DCJlKP+EsZXBAlIaUUpRoFU0CAWgWR0CPi4XgLqlhdX2UKGgGaAloD0MIPrSPFTxIckCUhpRSlGgVTQsBaBZHQI+MEtbs4T91fZQoaAZoCWgPQwhYrUz4JaZvQJSGlFKUaBVNSQFoFkdAj4x9sBQvYnV9lChoBmgJaA9DCGa8rfRa53BAlIaUUpRoFU0XAWgWR0CPjwXRgJC0dX2UKGgGaAloD0MIVyHlJ9VxckCUhpRSlGgVS+xoFkdAj5DRqfvnbXV9lChoBmgJaA9DCEfmkT8YzXFAlIaUUpRoFU0mAWgWR0CPkbBqKxcFdX2UKGgGaAloD0MI8DFYcWq2ckCUhpRSlGgVTS4BaBZHQI+SnB55Z8t1fZQoaAZoCWgPQwiuRQvQNtxvQJSGlFKUaBVNMwFoFkdAj5MAAZKnN3V9lChoBmgJaA9DCFQ4glSK1VBAlIaUUpRoFU3oA2gWR0CPk2yO7xusdX2UKGgGaAloD0MIUdobfCEZcUCUhpRSlGgVTQ0BaBZHQI+VsNhE0BR1fZQoaAZoCWgPQwgnvW987VlvQJSGlFKUaBVL+WgWR0CPldZ/0/W2dX2UKGgGaAloD0MICJEMObYyM0CUhpRSlGgVS8toFkdAj5dpI1+AmXV9lChoBmgJaA9DCAg57//jOkRAlIaUUpRoFUu/aBZHQI+YLundfsx1fZQoaAZoCWgPQwiPVUrPdG1xQJSGlFKUaBVNPgFoFkdAj5k0163RX3V9lChoBmgJaA9DCFvs9lllEm5AlIaUUpRoFUvzaBZHQI+Zl5a/yoZ1fZQoaAZoCWgPQwjV6UDWU4tVQJSGlFKUaBVL52gWR0CPmhDu0CzUdX2UKGgGaAloD0MIsBwhA3nybkCUhpRSlGgVTRkBaBZHQI+bCMtK7I11fZQoaAZoCWgPQwiale1DHhpyQJSGlFKUaBVNKgFoFkdAj50/Qa72+XV9lChoBmgJaA9DCPj/ccIEtnJAlIaUUpRoFU0LAWgWR0CPnqlpoK2KdX2UKGgGaAloD0MITSzwFd13b0CUhpRSlGgVTQsBaBZHQI+hGIGhVVB1fZQoaAZoCWgPQwgDste7P0xtQJSGlFKUaBVNDwFoFkdAj6I2qLjxTnV9lChoBmgJaA9DCFXcuMW84XJAlIaUUpRoFU0bAWgWR0CPo952Qnx8dX2UKGgGaAloD0MIKZSFr6/+cUCUhpRSlGgVS/xoFkdAj6SUwJw84nV9lChoBmgJaA9DCH+/mC2ZCHJAlIaUUpRoFUv+aBZHQI+k4Ahje9B1fZQoaAZoCWgPQwjULNDuUORwQJSGlFKUaBVNQQFoFkdAj6XnXEqDsnV9lChoBmgJaA9DCAiUTbnClXBAlIaUUpRoFU14AWgWR0CPp0oDPnjidX2UKGgGaAloD0MIZOlDF5S0cUCUhpRSlGgVTQ0BaBZHQI+oVk8Rtgt1fZQoaAZoCWgPQwipE9BE2OZLQJSGlFKUaBVLw2gWR0CPqv8m8dxRdX2UKGgGaAloD0MIwRvSqECYYkCUhpRSlGgVTegDaBZHQI+rSubI91V1fZQoaAZoCWgPQwgIPZtVHwRxQJSGlFKUaBVNIwFoFkdAj6tIw22oenV9lChoBmgJaA9DCA034POD83FAlIaUUpRoFU0IAWgWR0CPrZFbVz6rdX2UKGgGaAloD0MIIzFBDd+YcUCUhpRSlGgVTTYBaBZHQI+t6aRZED11fZQoaAZoCWgPQwjoMjUJHsVwQJSGlFKUaBVNdwFoFkdAj631twaR6nV9lChoBmgJaA9DCG/YtijzIXFAlIaUUpRoFU1wAWgWR0CPrySVW0Z4dX2UKGgGaAloD0MIFr8prJTVcECUhpRSlGgVTZoBaBZHQI+zmvOhTOx1fZQoaAZoCWgPQwjGia92lNFuQJSGlFKUaBVNIgFoFkdAj7PZssQNC3VlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "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": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (224 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 261.3381083799153, "std_reward": 11.8498643118098, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T08:13:23.492520"}
|