Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- 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
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
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: 204.41 +/- 37.60
|
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:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f16d0006440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f16d00064d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f16d0006560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f16d00065f0>", "_build": "<function ActorCriticPolicy._build at 0x7f16d0006680>", "forward": "<function ActorCriticPolicy.forward at 0x7f16d0006710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f16d00067a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f16d0006830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f16d00068c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f16d0006950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f16d00069e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f16d005b360>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653425784.881276, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df68300ce127575414e6fed8391512d21943a9abb209777bbf9cbbed3f5fd1f6
|
3 |
+
size 144127
|
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:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f16d0006440>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f16d00064d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f16d0006560>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f16d00065f0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f16d0006680>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f16d0006710>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f16d00067a0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f16d0006830>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f16d00068c0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f16d0006950>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f16d00069e0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f16d005b360>"
|
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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653425784.881276,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gASVaxAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIrkfhehTKNMCUhpRSlIwBbJRL0owBdJRHQKIh25QP7N11fZQoaAZoCWgPQwiaJ9cUyKVhQJSGlFKUaBVN6ANoFkdAoiLr0Bfa6HV9lChoBmgJaA9DCD6yuWqeAyJAlIaUUpRoFUvCaBZHQKIjZzp5eJJ1fZQoaAZoCWgPQwgZNzXQfBoxQJSGlFKUaBVLvmgWR0CiLy67dznzdX2UKGgGaAloD0MILgQ5KGHuX0CUhpRSlGgVTegDaBZHQKIvs03Ov+x1fZQoaAZoCWgPQwgOMPMd/DAzwJSGlFKUaBVLv2gWR0CiMAK7iADrdX2UKGgGaAloD0MIN6eSAaAKBsCUhpRSlGgVS7JoFkdAojF0AtFrmHV9lChoBmgJaA9DCOblsPuOCl9AlIaUUpRoFU3oA2gWR0CiMhbtRekYdX2UKGgGaAloD0MIe4SaIVWMQUCUhpRSlGgVS7toFkdAojV8t7KJVXV9lChoBmgJaA9DCKdYNQhzG2JAlIaUUpRoFU3oA2gWR0CiNY0z0pVkdX2UKGgGaAloD0MIA9AoXXoEY0CUhpRSlGgVTegDaBZHQKI2tsWO6up1fZQoaAZoCWgPQwjiV6zhIipbQJSGlFKUaBVN6ANoFkdAojmk65oXbnV9lChoBmgJaA9DCEPjiSDOUztAlIaUUpRoFUvTaBZHQKI7s8VYZEV1fZQoaAZoCWgPQwjnNXaJ6j01QJSGlFKUaBVL2GgWR0CiO+qkVN5/dX2UKGgGaAloD0MIjiCVYkdDGECUhpRSlGgVS81oFkdAojzCvzOHFnV9lChoBmgJaA9DCMtMaf0twFdAlIaUUpRoFU3oA2gWR0CiPgfrKNhmdX2UKGgGaAloD0MIm/9XHTl0XUCUhpRSlGgVTegDaBZHQKJCZsVtXPt1fZQoaAZoCWgPQwg6B8+EJgFjQJSGlFKUaBVN6ANoFkdAokKOITGo73V9lChoBmgJaA9DCJW6ZBwjbV5AlIaUUpRoFU3oA2gWR0CiQyi0fHPvdX2UKGgGaAloD0MI56c4DrzKXUCUhpRSlGgVTegDaBZHQKJEBwPRRdh1fZQoaAZoCWgPQwitwJDVrRdcQJSGlFKUaBVN6ANoFkdAokRNoJzDGnV9lChoBmgJaA9DCJccd0oH0UpAlIaUUpRoFUuyaBZHQKJG9q+rU9Z1fZQoaAZoCWgPQwhKJNHLqBZmQJSGlFKUaBVN6ANoFkdAokcEnqmj03V9lChoBmgJaA9DCMB4Bg39/2VAlIaUUpRoFU3oA2gWR0CiSCib2Dg7dX2UKGgGaAloD0MIbCIzF7iiXkCUhpRSlGgVTegDaBZHQKJLf4xDb8F1fZQoaAZoCWgPQwjfMxKhEeBjQJSGlFKUaBVN6ANoFkdAokwGhufmLnV9lChoBmgJaA9DCFsjgnFwT0NAlIaUUpRoFU3oA2gWR0CiVve/5+H8dX2UKGgGaAloD0MIy/J1Gf72WECUhpRSlGgVTegDaBZHQKJXmnO0LMN1fZQoaAZoCWgPQwgZda29T7NLQJSGlFKUaBVL+2gWR0CiXy4jrzGxdX2UKGgGaAloD0MIkx0bgfgAZUCUhpRSlGgVTegDaBZHQKJgO6V+qip1fZQoaAZoCWgPQwil3H2ODzJgQJSGlFKUaBVN6ANoFkdAomLDP8hs7HV9lChoBmgJaA9DCGtI3GNpMWFAlIaUUpRoFU3oA2gWR0CiYwl67dzodX2UKGgGaAloD0MI3ncMj/1yYkCUhpRSlGgVTegDaBZHQKJj9ZDiOvN1fZQoaAZoCWgPQwiI1oo2x/5jQJSGlFKUaBVN6ANoFkdAomVXFYMfBHV9lChoBmgJaA9DCLZoAdpWAxrAlIaUUpRoFUvKaBZHQKJpk7iADq51fZQoaAZoCWgPQwieRe9UwH1eQJSGlFKUaBVN6ANoFkdAomoORNh3JXV9lChoBmgJaA9DCHZTymslZFpAlIaUUpRoFU3oA2gWR0CiavYL1EmZdX2UKGgGaAloD0MIcm4T7pW/SkCUhpRSlGgVS7JoFkdAomshFZxJd3V9lChoBmgJaA9DCB3lYDaBwGBAlIaUUpRoFU3oA2gWR0CibA8zQ/ordX2UKGgGaAloD0MI6kFBKVoMXUCUhpRSlGgVTegDaBZHQKJsZk078vV1fZQoaAZoCWgPQwiBP/z890ldQJSGlFKUaBVN6ANoFkdAom9dGwzLwHV9lChoBmgJaA9DCFcG1QanDWNAlIaUUpRoFU3oA2gWR0Cib27NB4UvdX2UKGgGaAloD0MIO+C6YkYLUUCUhpRSlGgVTegDaBZHQKJwrFtsN2F1fZQoaAZoCWgPQwgLQQ5KmGE+QJSGlFKUaBVL3mgWR0CicVLBKtgbdX2UKGgGaAloD0MI/IugMZNcYkCUhpRSlGgVTegDaBZHQKJ0F0OmR/51fZQoaAZoCWgPQwgxQKIJFNpaQJSGlFKUaBVN6ANoFkdAonSr81n/UHV9lChoBmgJaA9DCN46/3bZcmBAlIaUUpRoFU3oA2gWR0CigGOo5xR3dX2UKGgGaAloD0MIdAtdiUDVCUCUhpRSlGgVS+1oFkdAooT5pWV/t3V9lChoBmgJaA9DCJ8B9WbUumJAlIaUUpRoFU3oA2gWR0CiiGadtl7MdX2UKGgGaAloD0MIOwDirl4ZNMCUhpRSlGgVS/loFkdAookZJqZc9nV9lChoBmgJaA9DCKcHBaXol2BAlIaUUpRoFU3oA2gWR0CiiVceKbazdX2UKGgGaAloD0MI56bNOA37YECUhpRSlGgVTegDaBZHQKKLi4Nqgyx1fZQoaAZoCWgPQwiEfqZet91VQJSGlFKUaBVN6ANoFkdAooyXO6d1+3V9lChoBmgJaA9DCBU42QbuUBRAlIaUUpRoFUvdaBZHQKKPQhCdBjZ1fZQoaAZoCWgPQwikVMITev1XQJSGlFKUaBVN6ANoFkdAopHu0mdAgXV9lChoBmgJaA9DCLB1qRF6oGJAlIaUUpRoFU3oA2gWR0Ciklllbu+idX2UKGgGaAloD0MIonxBCwkdX0CUhpRSlGgVTegDaBZHQKKTKybhFVl1fZQoaAZoCWgPQwjY74l1qlA+QJSGlFKUaBVL4GgWR0Cik2UcOskqdX2UKGgGaAloD0MIDB6mfXO+YkCUhpRSlGgVTegDaBZHQKKULNIsiB51fZQoaAZoCWgPQwjXprG9ljpiQJSGlFKUaBVN6ANoFkdAopR/oFFDv3V9lChoBmgJaA9DCLw7MlabSl1AlIaUUpRoFU3oA2gWR0CilybhWHUMdX2UKGgGaAloD0MInGotzEKIW0CUhpRSlGgVTegDaBZHQKKXM8dPtUp1fZQoaAZoCWgPQwgOpItNq6xiQJSGlFKUaBVN6ANoFkdAophQqLCN0nV9lChoBmgJaA9DCEELCRjdX2BAlIaUUpRoFU3oA2gWR0CimOJtix3WdX2UKGgGaAloD0MIB2ADIsQtI8CUhpRSlGgVTQQBaBZHQKKalXZGrjp1fZQoaAZoCWgPQwii7gOQ2hBdQJSGlFKUaBVN6ANoFkdAopu/3g1m8XV9lChoBmgJaA9DCBVYAFMGIEdAlIaUUpRoFUvEaBZHQKKmmOtnwod1fZQoaAZoCWgPQwi4zr9d9isgQJSGlFKUaBVL92gWR0CiprDgydnTdX2UKGgGaAloD0MILjcY6rDSLkCUhpRSlGgVS+doFkdAoqhM7wKBunV9lChoBmgJaA9DCP0WnSy11FZAlIaUUpRoFU3oA2gWR0Ciq2LaVUuMdX2UKGgGaAloD0MI7Z+nAYP4NkCUhpRSlGgVS7ZoFkdAoqwuIhyKenV9lChoBmgJaA9DCICAtWrXV19AlIaUUpRoFU3oA2gWR0CirwqFyq+8dX2UKGgGaAloD0MIBMb6BqbmYUCUhpRSlGgVTegDaBZHQKKvQ/rSmZV1fZQoaAZoCWgPQwjsFRbcD1tfQJSGlFKUaBVN6ANoFkdAorFS0Sh8IHV9lChoBmgJaA9DCGvwviqXzGFAlIaUUpRoFU3oA2gWR0CitS6zNUwSdX2UKGgGaAloD0MIrabria5wYUCUhpRSlGgVTegDaBZHQKK4Fv5P/Jh1fZQoaAZoCWgPQwh6pwLueU5VQJSGlFKUaBVN6ANoFkdAoriUdzXBg3V9lChoBmgJaA9DCII7UKc8tGBAlIaUUpRoFU3oA2gWR0CiuXY2jwhGdX2UKGgGaAloD0MITdu/stLOV0CUhpRSlGgVTegDaBZHQKK5tcoH9m91fZQoaAZoCWgPQwiqgHueP4FjQJSGlFKUaBVN6ANoFkdAorrlImPYF3V9lChoBmgJaA9DCNrk8EknAmRAlIaUUpRoFU3oA2gWR0Civk/3N9pidX2UKGgGaAloD0MIGm8rvTYwYECUhpRSlGgVTegDaBZHQKLC8UVzp5h1fZQoaAZoCWgPQwind/F+3OdeQJSGlFKUaBVN6ANoFkdAosR/nfVI7XV9lChoBmgJaA9DCHcP0H05dFtAlIaUUpRoFU3oA2gWR0CixnuUdJardX2UKGgGaAloD0MI/tR46Sb9XkCUhpRSlGgVTegDaBZHQKLRq8A7xNJ1fZQoaAZoCWgPQwjd66S+LN1fQJSGlFKUaBVN6ANoFkdAotULWoWHlHV9lChoBmgJaA9DCKn1fqOdv2FAlIaUUpRoFU3oA2gWR0Ci1d8UM5OrdX2UKGgGaAloD0MI0ZSdftBYYECUhpRSlGgVTegDaBZHQKLYpdLxqfx1fZQoaAZoCWgPQwhK0F/oEYBcQJSGlFKUaBVN6ANoFkdAotjhC4SYgXV9lChoBmgJaA9DCO5aQj7ohTFAlIaUUpRoFU3oA2gWR0Ci2vk2P1cudX2UKGgGaAloD0MI4+E9B5Y2Y0CUhpRSlGgVTegDaBZHQKLepCF9KEp1fZQoaAZoCWgPQwhbzxCOWepfQJSGlFKUaBVN6ANoFkdAouFEQoTfznV9lChoBmgJaA9DCIfguIybOV1AlIaUUpRoFU3oA2gWR0Ci4bQokRjCdX2UKGgGaAloD0MIAmcpWU7+VECUhpRSlGgVTegDaBZHQKLikXnhbW51fZQoaAZoCWgPQwjCTrFqEElYQJSGlFKUaBVN6ANoFkdAouLP3L3bmHV9lChoBmgJaA9DCMGsUKR7jmFAlIaUUpRoFU3oA2gWR0Ci4/B1LamGdX2UKGgGaAloD0MIH4E//Hx2YkCUhpRSlGgVTegDaBZHQKLm+gDA8CB1fZQoaAZoCWgPQwhh304iwitiQJSGlFKUaBVN6ANoFkdAoutI+IMz/XV9lChoBmgJaA9DCOF/K9mxo1tAlIaUUpRoFU3oA2gWR0Ci7MyLIgeSdX2UKGgGaAloD0MIfv578Np6XkCUhpRSlGgVTegDaBZHQKLuzEl3Qld1ZS4="
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 124,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
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:": "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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:b38d863357f7d08e0cf897c7244d0fcbbef5b81ff1664cae125f68222758bc11
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f239c0c99e0fe0ff92017bc5b987ccd9d87e6c591ae1205b89bd6b71e5750c9f
|
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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21a310c1620c8198c9434b592b14db2f8bf0560b2d8bfb391d5c44b8c3bb4559
|
3 |
+
size 165278
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 204.40970851336775, "std_reward": 37.601888610583906, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-24T21:40:20.997389"}
|