tuned LunarLander model trained with PPO
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 sha256:823ff352404354ab86c3b49e3095ca41aecff93b6d91aa053b3466548ecef3a2
|
3 |
+
size 147292
|
PPO-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.0
|
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 0x7f733ec72f80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f733ec73010>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f733ec730a0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f733ec73130>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f733ec731c0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f733ec73250>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f733ec732e0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f733ec73370>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f733ec73400>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f733ec73490>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f733ec73520>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f733ec6ec00>"
|
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": 1966080,
|
46 |
+
"_total_timesteps": 1954865,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1663629562.7035844,
|
51 |
+
"learning_rate": 0.002068243584637287,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gAWV7QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXS9ob21lL3JyYW0xMi9hbmFjb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMXS9ob21lL3JyYW0xMi9hbmFjb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/YPFr0cw3z4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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": -0.005736969049013663,
|
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": 420,
|
79 |
+
"n_steps": 2048,
|
80 |
+
"gamma": 0.9970099185201808,
|
81 |
+
"gae_lambda": 0.95,
|
82 |
+
"ent_coef": 0.0,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 7,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
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:cc2cd024f7b5173316544f3af1303378a0f58e23800bcc587fce1c06d99d7348
|
3 |
+
size 87865
|
PPO-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05d09286a9accd71319cbf260408ee056cb8560b0a0c67317a7a3c7f10cf7159
|
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-5.15.0-47-generic-x86_64-with-glibc2.35 #51-Ubuntu SMP Thu Aug 11 07:51:15 UTC 2022
|
2 |
+
Python: 3.10.4
|
3 |
+
Stable-Baselines3: 1.6.0
|
4 |
+
PyTorch: 1.12.1+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.23.3
|
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: 283.68 +/- 20.00
|
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 0x7f733ec72f80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f733ec73010>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f733ec730a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f733ec73130>", "_build": "<function ActorCriticPolicy._build at 0x7f733ec731c0>", "forward": "<function ActorCriticPolicy.forward at 0x7f733ec73250>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f733ec732e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f733ec73370>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f733ec73400>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f733ec73490>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f733ec73520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f733ec6ec00>"}, "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": 1966080, "_total_timesteps": 1954865, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1663629562.7035844, "learning_rate": 0.002068243584637287, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV7QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXS9ob21lL3JyYW0xMi9hbmFjb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMXS9ob21lL3JyYW0xMi9hbmFjb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/YPFr0cw3z4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_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": -0.005736969049013663, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 420, "n_steps": 2048, "gamma": 0.9970099185201808, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 7, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-47-generic-x86_64-with-glibc2.35 #51-Ubuntu SMP Thu Aug 11 07:51:15 UTC 2022", "Python": "3.10.4", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.1+cu116", "GPU Enabled": "True", "Numpy": "1.23.3", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (197 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 283.67660548661763, "std_reward": 19.99933910099818, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-09-20T02:52:52.918637"}
|