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 +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
- README.md +37 -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 sha256:8cee1074fb6379c1d2c4efb71cee44081a00b151d397a84c9dfe24385471eb78
|
3 |
+
size 145826
|
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 0x7f3ed5ad6430>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3ed5ad64c0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3ed5ad6550>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3ed5ad65e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3ed5ad6670>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3ed5ad6700>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3ed5ad6790>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3ed5ad6820>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3ed5ad68b0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3ed5ad6940>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3ed5ad69d0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3ed5ad6a60>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f3ed5ad4360>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
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": 1540096,
|
47 |
+
"_total_timesteps": 1524455,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1674302694911545949,
|
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:": "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"
|
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": -0.010260060152644801,
|
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": 376,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.998604713037232,
|
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 sha256:9790372ecd3830eef2936b6fc6d5701cd2d92011db40d76fea34d00996e2f81b
|
3 |
+
size 85735
|
PPO-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:079df1b812e052b7658a7c6c2748b956ef72d3cc3d5a023330da9cc2f6c13514
|
3 |
+
size 44075
|
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-5.13.0-30-generic-x86_64-with-glibc2.29 # 33~20.04.1-Ubuntu SMP Mon Feb 7 14:25:10 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.8.1+cu102
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
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: 269.37 +/- 23.86
|
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 0x7f3ed5ad6430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3ed5ad64c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3ed5ad6550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3ed5ad65e0>", "_build": "<function ActorCriticPolicy._build at 0x7f3ed5ad6670>", "forward": "<function ActorCriticPolicy.forward at 0x7f3ed5ad6700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3ed5ad6790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3ed5ad6820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3ed5ad68b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3ed5ad6940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3ed5ad69d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3ed5ad6a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3ed5ad4360>"}, "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": 1540096, "_total_timesteps": 1524455, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1674302694911545949, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVqgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMeC9ob21lL2FjbC9EZXNrdG9wL3JvYm90LWxlYXJuaW5nL2h1Z2dpbmdmYWNlLzEubHVuYXJsYW5kZXIvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB59lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_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": -0.010260060152644801, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 376, "n_steps": 1024, "gamma": 0.998604713037232, "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:": "gAWVqgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMeC9ob21lL2FjbC9EZXNrdG9wL3JvYm90LWxlYXJuaW5nL2h1Z2dpbmdmYWNlLzEubHVuYXJsYW5kZXIvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB59lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-30-generic-x86_64-with-glibc2.29 # 33~20.04.1-Ubuntu SMP Mon Feb 7 14:25:10 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.8.1+cu102", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (229 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 269.3727785550214, "std_reward": 23.85960366546086, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-21T21:23:15.558525"}
|