Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v1_snicolau.zip +3 -0
- ppo-LunarLander-v1_snicolau/_stable_baselines3_version +1 -0
- ppo-LunarLander-v1_snicolau/data +95 -0
- ppo-LunarLander-v1_snicolau/policy.optimizer.pth +3 -0
- ppo-LunarLander-v1_snicolau/policy.pth +3 -0
- ppo-LunarLander-v1_snicolau/pytorch_variables.pth +3 -0
- ppo-LunarLander-v1_snicolau/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: 258.67 +/- 18.31
|
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 0x7f04a89d9a60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f04a89d9af0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f04a89d9b80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f04a89d9c10>", "_build": "<function ActorCriticPolicy._build at 0x7f04a89d9ca0>", "forward": "<function ActorCriticPolicy.forward at 0x7f04a89d9d30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f04a89d9dc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f04a89d9e50>", "_predict": "<function ActorCriticPolicy._predict at 0x7f04a89d9ee0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f04a89d9f70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f04a89df040>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f04a89df0d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f04a89dac40>"}, "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": 1678847265546012340, "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, "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-v1_snicolau.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feffa4473368e96dd10c1e787fdb2715b5aba45aa41056583ee5ef14e1c8bca7
|
3 |
+
size 147417
|
ppo-LunarLander-v1_snicolau/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v1_snicolau/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 0x7f04a89d9a60>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f04a89d9af0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f04a89d9b80>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f04a89d9c10>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f04a89d9ca0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f04a89d9d30>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f04a89d9dc0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f04a89d9e50>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f04a89d9ee0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f04a89d9f70>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f04a89df040>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f04a89df0d0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f04a89dac40>"
|
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": 1678847265546012340,
|
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": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "gAWVdhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIy2Wjc/50YECUhpRSlIwBbJRN6AOMAXSUR0CSZ6NSZSeidX2UKGgGaAloD0MIxca8jnhqcUCUhpRSlGgVTTIDaBZHQJJpw6BAfMh1fZQoaAZoCWgPQwhRhT/Dm1tOQJSGlFKUaBVLtWgWR0CScaaUiY9gdX2UKGgGaAloD0MImgtcHus2Z0CUhpRSlGgVTegDaBZHQJJycDfWMCN1fZQoaAZoCWgPQwhYU1kUduxnQJSGlFKUaBVN6ANoFkdAknTIuXeFc3V9lChoBmgJaA9DCOv/HObLg09AlIaUUpRoFUvBaBZHQJJ1stJ4B3l1fZQoaAZoCWgPQwixFTQtsRxhQJSGlFKUaBVN6ANoFkdAkncRYigTRXV9lChoBmgJaA9DCM6qz9VWS2RAlIaUUpRoFU3oA2gWR0CSgCybx3FDdX2UKGgGaAloD0MIlScQdoqeaECUhpRSlGgVTegDaBZHQJKBuiYb83x1fZQoaAZoCWgPQwi0yeGTzi5iQJSGlFKUaBVN6ANoFkdAkoRLehwl0HV9lChoBmgJaA9DCAVSYtf2dGJAlIaUUpRoFU3oA2gWR0CShob9If8udX2UKGgGaAloD0MIu0VgrG/qX0CUhpRSlGgVTegDaBZHQJKdpmkFfRh1fZQoaAZoCWgPQwj/Qo8YPexhQJSGlFKUaBVN6ANoFkdAkqA8xoIv8XV9lChoBmgJaA9DCB9kWTDxH2RAlIaUUpRoFU3oA2gWR0CSoiPKdQO4dX2UKGgGaAloD0MIWVLuPsdhS0CUhpRSlGgVS+BoFkdAkqT8JUo8ZHV9lChoBmgJaA9DCB0+6UQCU2lAlIaUUpRoFU3oA2gWR0CSqqeFL39KdX2UKGgGaAloD0MIJvvnacBIY0CUhpRSlGgVTegDaBZHQJK5KqzZ6D51fZQoaAZoCWgPQwg8TzxnC1NlQJSGlFKUaBVN6ANoFkdAkrqZ0Syt3nV9lChoBmgJaA9DCKIMVTGVil9AlIaUUpRoFU3oA2gWR0CSvGM8YAKfdX2UKGgGaAloD0MIvmplwq85ZUCUhpRSlGgVTegDaBZHQJLI2DpTuOV1fZQoaAZoCWgPQwjXhLTGoLlmQJSGlFKUaBVN6ANoFkdAksl6t1ZDA3V9lChoBmgJaA9DCEJClC/oVGFAlIaUUpRoFU3oA2gWR0CSy0XJo0yhdX2UKGgGaAloD0MIDeIDO37/ZECUhpRSlGgVTegDaBZHQJLL++BYmsx1fZQoaAZoCWgPQwiJQWDl0BxlQJSGlFKUaBVN6ANoFkdAkszlFpfx+nV9lChoBmgJaA9DCEwW9x+ZlGZAlIaUUpRoFU3oA2gWR0CS0oWUr08OdX2UKGgGaAloD0MIGuHtQYguZ0CUhpRSlGgVTegDaBZHQJLTb8zhxYJ1fZQoaAZoCWgPQwjU78LW7DxoQJSGlFKUaBVN6ANoFkdAktVIWcjJMnV9lChoBmgJaA9DCKTk1TkGimFAlIaUUpRoFU3oA2gWR0CS8PYrrgO0dX2UKGgGaAloD0MIfnA+dSz2ZUCUhpRSlGgVTegDaBZHQJL0kG4ZuQ91fZQoaAZoCWgPQwiwIM1YtI1kQJSGlFKUaBVN6ANoFkdAkvc+9vjwQXV9lChoBmgJaA9DCGptGttrDmVAlIaUUpRoFU3oA2gWR0CS+me2/i5vdX2UKGgGaAloD0MIW5iFds4TZUCUhpRSlGgVTegDaBZHQJL/Q6vJRwZ1fZQoaAZoCWgPQwgkJqjhWyBAQJSGlFKUaBVLv2gWR0CTBC0v4/NadX2UKGgGaAloD0MIw35PrNOBZECUhpRSlGgVTegDaBZHQJMIKR4hUzd1fZQoaAZoCWgPQwiJXdvbrcVoQJSGlFKUaBVN6ANoFkdAkwkIG+sYEXV9lChoBmgJaA9DCNs0ttcCjGNAlIaUUpRoFU3oA2gWR0CTCh0hePaMdX2UKGgGaAloD0MI4uoAiLsKHUCUhpRSlGgVS9xoFkdAkxByk9ECvHV9lChoBmgJaA9DCM5SspyE8VBAlIaUUpRoFUvBaBZHQJMTxtXPqs51fZQoaAZoCWgPQwgaMbPP4+1kQJSGlFKUaBVN6ANoFkdAkxSQ8W9DhXV9lChoBmgJaA9DCDXwoxp2yWJAlIaUUpRoFU3oA2gWR0CTFSRXwLE2dX2UKGgGaAloD0MIcEIhAg5uXUCUhpRSlGgVTegDaBZHQJMWtmYjSoh1fZQoaAZoCWgPQwgKvmn6bJRjQJSGlFKUaBVN6ANoFkdAkxdCRGMGYHV9lChoBmgJaA9DCKZiY17H02RAlIaUUpRoFU3oA2gWR0CTF/2/BWPtdX2UKGgGaAloD0MI43FRLSKaT0CUhpRSlGgVS91oFkdAkxsscp9ZzXV9lChoBmgJaA9DCM7DCUynm2JAlIaUUpRoFU3oA2gWR0CTHOv73wkPdX2UKGgGaAloD0MI+pl63SIbZECUhpRSlGgVTegDaBZHQJMdx8PWhAZ1fZQoaAZoCWgPQwhd3EYDeBlbQJSGlFKUaBVN6ANoFkdAkx9qfzz3AXV9lChoBmgJaA9DCNkIxOv6X0VAlIaUUpRoFUvoaBZHQJMgf6Mzdk91fZQoaAZoCWgPQwgnwoanV7pmQJSGlFKUaBVN6ANoFkdAkyd4zabnYHV9lChoBmgJaA9DCGpPyTmxa2JAlIaUUpRoFU3oA2gWR0CTQLmiQDFIdX2UKGgGaAloD0MIuMt+3Wm9YUCUhpRSlGgVTegDaBZHQJNCo5eZ5Rl1fZQoaAZoCWgPQwiIgEOoUj1JQJSGlFKUaBVLyWgWR0CTSRAtWdVedX2UKGgGaAloD0MIEmvxKQBlX0CUhpRSlGgVTegDaBZHQJNK08gZCOZ1fZQoaAZoCWgPQwhQ5EnStYtkQJSGlFKUaBVN6ANoFkdAk1QcTrVvuXV9lChoBmgJaA9DCKUvhJx3nGhAlIaUUpRoFU3oA2gWR0CTVhMGX5WSdX2UKGgGaAloD0MIz79d9mvfYkCUhpRSlGgVTegDaBZHQJNiWmYSg5B1fZQoaAZoCWgPQwibV3VWC29hQJSGlFKUaBVN6ANoFkdAk2OOAI6bOXV9lChoBmgJaA9DCIZxN4hWk2FAlIaUUpRoFU3oA2gWR0CTZGFcpsoEdX2UKGgGaAloD0MISUkPQ6uYWkCUhpRSlGgVTegDaBZHQJNoIVQAMlV1fZQoaAZoCWgPQwgL1c3F31ljQJSGlFKUaBVN6ANoFkdAk2mgC0WuYHV9lChoBmgJaA9DCOJYF7dRp2FAlIaUUpRoFU3oA2gWR0CTb37SApazdX2UKGgGaAloD0MIbHnleluyZUCUhpRSlGgVTegDaBZHQJNxra0x/NJ1fZQoaAZoCWgPQwhNMnIWdsBiQJSGlFKUaBVN6ANoFkdAk3K0OmR/3HV9lChoBmgJaA9DCKlsWFNZLl1AlIaUUpRoFU3oA2gWR0CTdMjnV5KOdX2UKGgGaAloD0MIgqlm1tLNZkCUhpRSlGgVTegDaBZHQJN2GsMiKSB1fZQoaAZoCWgPQwjkaI6s/MBiQJSGlFKUaBVN6ANoFkdAk5GBC6YmcHV9lChoBmgJaA9DCO7O2m2XCGJAlIaUUpRoFU3oA2gWR0CTk+Ea2nbZdX2UKGgGaAloD0MI2PD0SlkGYkCUhpRSlGgVTegDaBZHQJOd2oESuhd1fZQoaAZoCWgPQwiV056Sc6JhQJSGlFKUaBVN6ANoFkdAk6CvtQbdanV9lChoBmgJaA9DCPkvEARI1GBAlIaUUpRoFU3oA2gWR0CTrz5+H8CQdX2UKGgGaAloD0MIfPKwUGsnZECUhpRSlGgVTegDaBZHQJOxtRUFSsN1fZQoaAZoCWgPQwg6V5QSAhJjQJSGlFKUaBVN6ANoFkdAk713fZVXFXV9lChoBmgJaA9DCGr3qwDfJGdAlIaUUpRoFU3oA2gWR0CTvmA+Y+jedX2UKGgGaAloD0MIQX+hRwzKZECUhpRSlGgVTegDaBZHQJO+9Lg4wRJ1fZQoaAZoCWgPQwiZucDlseRjQJSGlFKUaBVN6ANoFkdAk8FtMfzSTnV9lChoBmgJaA9DCC2VtyMcZmJAlIaUUpRoFU3oA2gWR0CTwm1xsEaEdX2UKGgGaAloD0MIj1AzpApUY0CUhpRSlGgVTegDaBZHQJPG3QQcxTN1fZQoaAZoCWgPQwjIX1rUp2xnQJSGlFKUaBVN6ANoFkdAk8j2j4593XV9lChoBmgJaA9DCBvZlZYRPmJAlIaUUpRoFU3oA2gWR0CTyfSJCSiedX2UKGgGaAloD0MIFhdH5aZnYkCUhpRSlGgVTegDaBZHQJPL1P2wmmd1fZQoaAZoCWgPQwjIKM+8nBFmQJSGlFKUaBVN6ANoFkdAk80GzOX3QHV9lChoBmgJaA9DCI7NjlTfgGJAlIaUUpRoFU3oA2gWR0CT1hdPci4bdX2UKGgGaAloD0MITdwqiIG0YECUhpRSlGgVTegDaBZHQJPvIzBRAKR1fZQoaAZoCWgPQwhzLzArFBE2QJSGlFKUaBVL72gWR0CT8bmNR3vAdX2UKGgGaAloD0MILjvEP2y8YkCUhpRSlGgVTegDaBZHQJP1qwyIpH91fZQoaAZoCWgPQwg49uy5TDVoQJSGlFKUaBVN6ANoFkdAk/djINmUW3V9lChoBmgJaA9DCKHa4ET09VJAlIaUUpRoFUvDaBZHQJP8cVWS2Yx1fZQoaAZoCWgPQwhcqz3shc9iQJSGlFKUaBVN6ANoFkdAlABRZ+x4ZHV9lChoBmgJaA9DCFiqC3iZU2VAlIaUUpRoFU3oA2gWR0CUAjCUornUdX2UKGgGaAloD0MIPbZlwFkoZkCUhpRSlGgVTegDaBZHQJQMDaIvalF1fZQoaAZoCWgPQwivd3+8VxtfQJSGlFKUaBVN6ANoFkdAlA0FdcB2fXV9lChoBmgJaA9DCIOKql9pm2ZAlIaUUpRoFU3oA2gWR0CUDeSn+AEudX2UKGgGaAloD0MIvqQxWkchY0CUhpRSlGgVTegDaBZHQJQRUW1twaR1fZQoaAZoCWgPQwjUJ7nDJqJgQJSGlFKUaBVN6ANoFkdAlBKrNB4UvnV9lChoBmgJaA9DCJ+RCI1gdGNAlIaUUpRoFU3oA2gWR0CUGJ1vl2eQdX2UKGgGaAloD0MIMc10rxNbZUCUhpRSlGgVTegDaBZHQJQbxQvYe1d1fZQoaAZoCWgPQwj6Qsh5f6NnQJSGlFKUaBVN6ANoFkdAlB1Q+hXbNHV9lChoBmgJaA9DCAppjUEni11AlIaUUpRoFU3oA2gWR0CUIB5rgwXZdX2UKGgGaAloD0MIC0YldYIVZECUhpRSlGgVTegDaBZHQJQqcHu7YkF1fZQoaAZoCWgPQwhgdk8eFnBiQJSGlFKUaBVN6ANoFkdAlCyvetSydHVlLg=="
|
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-v1_snicolau/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2152e09557f6cb7a8ff15731d39aa579e7895aa0cdddefb3845e4976244479e1
|
3 |
+
size 87929
|
ppo-LunarLander-v1_snicolau/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34f979bccb3443fe393d5781b34b98be5c6bc0f0b46ab0dbc2b8b4cff8a455f6
|
3 |
+
size 43393
|
ppo-LunarLander-v1_snicolau/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-v1_snicolau/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 (195 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 258.67217986279763, "std_reward": 18.31286009934337, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-15T02:53:37.901790"}
|