First Trial of Lunar Lander
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: 252.63 +/- 24.49
|
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 0x7fa70dc4d710>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa70dc4d7a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa70dc4d830>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa70dc4d8c0>", "_build": "<function ActorCriticPolicy._build at 0x7fa70dc4d950>", "forward": "<function ActorCriticPolicy.forward at 0x7fa70dc4d9e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa70dc4da70>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa70dc4db00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa70dc4db90>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa70dc4dc20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa70dc4dcb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fa70dc9b840>"}, "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": 1654688276.7338293, "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": 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-5.4.188+-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:c29c300d1ee07db9285926e76c397d1698ecd527d56f4ac385ddf4c9027237e3
|
3 |
+
size 144156
|
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 0x7fa70dc4d710>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa70dc4d7a0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa70dc4d830>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa70dc4d8c0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fa70dc4d950>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fa70dc4d9e0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa70dc4da70>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fa70dc4db00>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa70dc4db90>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa70dc4dc20>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa70dc4dcb0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fa70dc9b840>"
|
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": 1654688276.7338293,
|
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:": "gASVgBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIpP0PsNa5YUCUhpRSlIwBbJRN6AOMAXSUR0CRRf1PWQOndX2UKGgGaAloD0MIXYjVH2HOYkCUhpRSlGgVTegDaBZHQJFGUMz/IbR1fZQoaAZoCWgPQwgAHebLCz9fQJSGlFKUaBVN6ANoFkdAkUsV2vB7/nV9lChoBmgJaA9DCJrQJLEkP2NAlIaUUpRoFU3oA2gWR0CRTOENvwVkdX2UKGgGaAloD0MIZjGx+bhAXECUhpRSlGgVTegDaBZHQJFOLoMa0hN1fZQoaAZoCWgPQwg4LA38KFNhQJSGlFKUaBVN6ANoFkdAkVe/sNUfgnV9lChoBmgJaA9DCGR5Vz1gR15AlIaUUpRoFU3oA2gWR0CRWLssg+yJdX2UKGgGaAloD0MIhbLw9TUnZkCUhpRSlGgVTegDaBZHQJFa6CJ40Mx1fZQoaAZoCWgPQwiXyXA8n1lhQJSGlFKUaBVN6ANoFkdAkVs4e1a4c3V9lChoBmgJaA9DCKnCn+GNznFAlIaUUpRoFU0QAmgWR0CRX8mJ3xFzdX2UKGgGaAloD0MIdlPKa6XEZkCUhpRSlGgVTegDaBZHQJFg91oxpL51fZQoaAZoCWgPQwg+sU6Vb3hvQJSGlFKUaBVN1AJoFkdAkWj1BUrCnHV9lChoBmgJaA9DCFhUxOmkimVAlIaUUpRoFU3oA2gWR0CRbmIDYAbRdX2UKGgGaAloD0MITpzc71C/XkCUhpRSlGgVTegDaBZHQJGJyZE2Hcl1fZQoaAZoCWgPQwhFn48yYi5kQJSGlFKUaBVN6ANoFkdAkYvz/uLJjnV9lChoBmgJaA9DCEvJchLKxGFAlIaUUpRoFU3oA2gWR0CRjBbi6xxDdX2UKGgGaAloD0MIVP8gkiFccECUhpRSlGgVTSQCaBZHQJGNpjz7MxJ1fZQoaAZoCWgPQwi4dTdP9XFlQJSGlFKUaBVN6ANoFkdAkY/1y/9Hc3V9lChoBmgJaA9DCLPROT/FLGZAlIaUUpRoFU3oA2gWR0CRkEPj4pMIdX2UKGgGaAloD0MIjiCVYkfSakCUhpRSlGgVTYYDaBZHQJGRejBVMmF1fZQoaAZoCWgPQwj9SufDs5xtQJSGlFKUaBVNqwNoFkdAkZU3G4qgAnV9lChoBmgJaA9DCDRmEvWCgmRAlIaUUpRoFU3oA2gWR0CRmcTZg5R1dX2UKGgGaAloD0MIJlXbTfBKbUCUhpRSlGgVTd4BaBZHQJGc7gTAWSF1fZQoaAZoCWgPQwgFGJY/32ZyQJSGlFKUaBVNmgFoFkdAkaGtYKYzBXV9lChoBmgJaA9DCFpkO9+PEHFAlIaUUpRoFU2fA2gWR0CRpCOpbUw0dX2UKGgGaAloD0MIt5c0RmvXYkCUhpRSlGgVTegDaBZHQJGks80UGml1fZQoaAZoCWgPQwizJasi3PhiQJSGlFKUaBVN6ANoFkdAkagdm16VuHV9lChoBmgJaA9DCAb3Ax7Y73BAlIaUUpRoFU3SA2gWR0CRrALteD3/dX2UKGgGaAloD0MIMzMzM7PiZkCUhpRSlGgVTegDaBZHQJGugK6WgOB1fZQoaAZoCWgPQwhHyatzDCBGQJSGlFKUaBVNEgFoFkdAkbOoZQ53knV9lChoBmgJaA9DCMecZ+zLo21AlIaUUpRoFU3bAmgWR0CRs/RP420idX2UKGgGaAloD0MI7kEIyFd4cUCUhpRSlGgVTdoDaBZHQJG1XSofjjt1fZQoaAZoCWgPQwiDNGPRdMlwQJSGlFKUaBVN/QJoFkdAkbc867ulXXV9lChoBmgJaA9DCKG5TiNt73BAlIaUUpRoFU0IA2gWR0CRunAc1fmcdX2UKGgGaAloD0MIBKvq5ffDb0CUhpRSlGgVTR0DaBZHQJG7Q+iaiK11fZQoaAZoCWgPQwgHtHQF2/tiQJSGlFKUaBVN6ANoFkdAkdOTkdV/+nV9lChoBmgJaA9DCMjNcAM+X3BAlIaUUpRoFU2HAmgWR0CR0+WeHzpYdX2UKGgGaAloD0MIgqrRqwGsa0CUhpRSlGgVTT0DaBZHQJHVeNEPUa11fZQoaAZoCWgPQwj44ov2+EdwQJSGlFKUaBVNxAFoFkdAkdc+OGTLXHV9lChoBmgJaA9DCEG2LF8X5G1AlIaUUpRoFU0dAmgWR0CR2FDfWMCLdX2UKGgGaAloD0MIEeULWsjCbkCUhpRSlGgVTVwCaBZHQJHYjmCAc1h1fZQoaAZoCWgPQwjT3AphdWVwQJSGlFKUaBVNUwFoFkdAkdjEo0ALiXV9lChoBmgJaA9DCH8XtmarHWJAlIaUUpRoFU3oA2gWR0CR2efvnbItdX2UKGgGaAloD0MIDybFx6cmb0CUhpRSlGgVTboCaBZHQJHaYE8q4H51fZQoaAZoCWgPQwiXH7jKUxdxQJSGlFKUaBVNJgFoFkdAkdutjCpFTnV9lChoBmgJaA9DCPZGrTB92m5AlIaUUpRoFU0pAWgWR0CR3FPjXFtLdX2UKGgGaAloD0MIn6pCA7GaTUCUhpRSlGgVS8JoFkdAkdyOSOinHnV9lChoBmgJaA9DCEEMdO0LyFtAlIaUUpRoFU3oA2gWR0CR4HqXnhbXdX2UKGgGaAloD0MIdsJLcGqZb0CUhpRSlGgVTX4CaBZHQJHgj6TGHYZ1fZQoaAZoCWgPQwjwayQJwuhuQJSGlFKUaBVNeAJoFkdAkeRWyX2M9HV9lChoBmgJaA9DCHxinSqfTnJAlIaUUpRoFU1hAmgWR0CR5L1ZTyavdX2UKGgGaAloD0MILA/SU2SUbkCUhpRSlGgVTXwBaBZHQJHqh2+wkgR1fZQoaAZoCWgPQwiWk1D6gjZwQJSGlFKUaBVNZwFoFkdAkevqpcX3xnV9lChoBmgJaA9DCKVN1T2yHWxAlIaUUpRoFU3pAWgWR0CR7ra5wwTNdX2UKGgGaAloD0MIjQkxl1QdbkCUhpRSlGgVTS4CaBZHQJHyuVyFPBV1fZQoaAZoCWgPQwjp0r8klfEtQJSGlFKUaBVNCwFoFkdAkfL6R+z+m3V9lChoBmgJaA9DCFSthVlo521AlIaUUpRoFU32AWgWR0CR9JUrkKeDdX2UKGgGaAloD0MIhPQUOcT5cUCUhpRSlGgVTZcCaBZHQJH0w7EHdGl1fZQoaAZoCWgPQwhQHauU3lBxQJSGlFKUaBVNjQJoFkdAkfb82zfJm3V9lChoBmgJaA9DCIWwGkvYt25AlIaUUpRoFU03AmgWR0CR+BAggX/HdX2UKGgGaAloD0MIqtOBrCeAY0CUhpRSlGgVTegDaBZHQJH6zDO1OTJ1fZQoaAZoCWgPQwglP+JXrEFOQJSGlFKUaBVNKwFoFkdAkftLApKBd3V9lChoBmgJaA9DCIxNK4XAjXFAlIaUUpRoFU0jAWgWR0CR/W8BdUsGdX2UKGgGaAloD0MIQUmBBTA3bECUhpRSlGgVTZ8DaBZHQJH/+aF23a11fZQoaAZoCWgPQwjlKavp+jhwQJSGlFKUaBVNjwNoFkdAkgLak/KQrHV9lChoBmgJaA9DCPyPTIeOu3BAlIaUUpRoFU1FAWgWR0CSAwCV8kUsdX2UKGgGaAloD0MIuk24V2Z7cUCUhpRSlGgVTVEBaBZHQJIDwymALAp1fZQoaAZoCWgPQwgFi8OZnwJzQJSGlFKUaBVNmgNoFkdAkhleuA7Pp3V9lChoBmgJaA9DCBCugEI9525AlIaUUpRoFU0TAWgWR0CSG5Drqt5ldX2UKGgGaAloD0MIzCbAsPw8cECUhpRSlGgVTaQBaBZHQJIb61F6Rhd1fZQoaAZoCWgPQwh2UfTAx8psQJSGlFKUaBVNewFoFkdAkhxC+Yc/+3V9lChoBmgJaA9DCFn4+lrX5nFAlIaUUpRoFU1NA2gWR0CSHTg00m+kdX2UKGgGaAloD0MIngyOkhe4cUCUhpRSlGgVTdUBaBZHQJIeJIqbz9V1fZQoaAZoCWgPQwjhYkUNJkNuQJSGlFKUaBVNagFoFkdAkh7ICyQgcXV9lChoBmgJaA9DCLUYPEx7l3JAlIaUUpRoFU1+A2gWR0CSHx6O5rgwdX2UKGgGaAloD0MI6NzteumnbUCUhpRSlGgVTYcBaBZHQJIiCC9RJmN1fZQoaAZoCWgPQwg6kzZV9xVsQJSGlFKUaBVNcQNoFkdAkiIc2rGR3nV9lChoBmgJaA9DCOeLvRffv21AlIaUUpRoFU1CAWgWR0CSJBxuKoAGdX2UKGgGaAloD0MIbqXXZuM/bkCUhpRSlGgVTVcBaBZHQJIkJoEjgQ91fZQoaAZoCWgPQwg8MlabvxlxQJSGlFKUaBVNpwFoFkdAkiUBSUC7snV9lChoBmgJaA9DCKg5eZEJF25AlIaUUpRoFU1sA2gWR0CSJjkcS5AhdX2UKGgGaAloD0MIzjRh+8m7cUCUhpRSlGgVTSIBaBZHQJInU+8oQWh1fZQoaAZoCWgPQwhpNo/DYOhwQJSGlFKUaBVNPAFoFkdAkif6akRBeHV9lChoBmgJaA9DCAmH3uLhEnFAlIaUUpRoFU3+AmgWR0CSLCwnYxtYdX2UKGgGaAloD0MIrkoi+6COb0CUhpRSlGgVTYwBaBZHQJIsn4xk/bF1fZQoaAZoCWgPQwiYamYtRThyQJSGlFKUaBVNYQFoFkdAkizN4iX6ZnV9lChoBmgJaA9DCBKgppYtrHFAlIaUUpRoFU3sAWgWR0CSLy50bLlndX2UKGgGaAloD0MIPZl/9M0KbkCUhpRSlGgVTVIBaBZHQJIvahWYF7l1fZQoaAZoCWgPQwib6PNRRtFvQJSGlFKUaBVNRAJoFkdAkjD0Syt3fXV9lChoBmgJaA9DCDKuuDhqxHFAlIaUUpRoFU1WAWgWR0CSMfWU8mrsdX2UKGgGaAloD0MIIPDAAML1b0CUhpRSlGgVTZEBaBZHQJIyJWwNb1R1fZQoaAZoCWgPQwgaahSSzOxvQJSGlFKUaBVNGgFoFkdAkjPexGDtgXV9lChoBmgJaA9DCGA5QgZyP3BAlIaUUpRoFU2OAWgWR0CSNDAiV0LddX2UKGgGaAloD0MIveMUHYkicECUhpRSlGgVTTYCaBZHQJI1SA/cFhZ1fZQoaAZoCWgPQwiLwi6KnkNuQJSGlFKUaBVNkgFoFkdAkjVGE0zj3nV9lChoBmgJaA9DCGa7Qh9srHJAlIaUUpRoFU1NAmgWR0CSNX9Wp6yCdX2UKGgGaAloD0MIOBQ+WweXP0CUhpRSlGgVTQQBaBZHQJI3QB0ZFXt1fZQoaAZoCWgPQwjPLt/6sLBvQJSGlFKUaBVNmAFoFkdAkjfKWw/xD3V9lChoBmgJaA9DCH+g3LZvjmFAlIaUUpRoFU3oA2gWR0CSPpdepn6EdX2UKGgGaAloD0MIIm5OJQOYcUCUhpRSlGgVTV0BaBZHQJI/A2FWXC11ZS4="
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 248,
|
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 sha256:33bf55948f963c5d392af57367d535fdb0789b6b184a51b8261de66dd8a124cb
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:497d99ae028880f41e0078ee85f116cb396d79aef98c1b3257790b488caff0d0
|
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 sha256:49e18176a9adc1dd5ce6af6756109363ec9cafebacb34493057221c6ad94d34a
|
3 |
+
size 195054
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 252.62927954094985, "std_reward": 24.48618921921519, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-08T11:50:12.062025"}
|