rachmanilove
commited on
Commit
·
015f150
1
Parent(s):
1ffdec7
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -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 +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: 263.34 +/- 24.62
|
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 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 0x7fcc1cf93040>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc1cf930d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc1cf93160>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc1cf931f0>", "_build": "<function ActorCriticPolicy._build at 0x7fcc1cf93280>", "forward": "<function ActorCriticPolicy.forward at 0x7fcc1cf93310>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc1cf933a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcc1cf93430>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc1cf934c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc1cf93550>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc1cf935e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcc1cf8c5a0>"}, "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": 1671569597549427277, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 sha256:1422928a4b2ecc6dde14a8dd80911f97009c62ad33c629b8478502b573bf222f
|
3 |
+
size 147206
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
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 0x7fcc1cf93040>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc1cf930d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc1cf93160>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc1cf931f0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fcc1cf93280>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fcc1cf93310>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc1cf933a0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fcc1cf93430>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc1cf934c0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc1cf93550>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc1cf935e0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fcc1cf8c5a0>"
|
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": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1671569597549427277,
|
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:": "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": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gAWVeBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMItmeWBCgXZ0CUhpRSlIwBbJRN6AOMAXSUR0CPvrjHXEqEdX2UKGgGaAloD0MIWvCir6C0YUCUhpRSlGgVTegDaBZHQI/Ck163RXx1fZQoaAZoCWgPQwiBs5QsJ8xfQJSGlFKUaBVN6ANoFkdAj8OtTLns9nV9lChoBmgJaA9DCJD4FWu4UkVAlIaUUpRoFUvZaBZHQI/EUI5YHPh1fZQoaAZoCWgPQwghrMYS1nYVQJSGlFKUaBVL7GgWR0CPynKCg9NfdX2UKGgGaAloD0MIU8xB0FFiYUCUhpRSlGgVTegDaBZHQI/MLB9Cu2Z1fZQoaAZoCWgPQwi4zVSIx5dmQJSGlFKUaBVN6ANoFkdAj8xH3L3bmHV9lChoBmgJaA9DCJhokIKnJ2ZAlIaUUpRoFU3oA2gWR0CPzWU9IPK/dX2UKGgGaAloD0MIGRwlr87MYUCUhpRSlGgVTegDaBZHQI/StLzwtrd1fZQoaAZoCWgPQwiNuAA0Sj5mQJSGlFKUaBVN6ANoFkdAj9iX7cfvF3V9lChoBmgJaA9DCPX3UnhQQmRAlIaUUpRoFU3oA2gWR0CP55HoX9BKdX2UKGgGaAloD0MIAHUDBd5pYUCUhpRSlGgVTegDaBZHQI/wusT37DV1fZQoaAZoCWgPQwgbZf1mYgBhQJSGlFKUaBVN6ANoFkdAj/LXGwRoRXV9lChoBmgJaA9DCKbvNQTH4GJAlIaUUpRoFU3oA2gWR0CQE/274BV/dX2UKGgGaAloD0MIvqQxWsdIYkCUhpRSlGgVTegDaBZHQJAfZTQ3PzF1fZQoaAZoCWgPQwi/SGjLObdlQJSGlFKUaBVN6ANoFkdAkCToZMtbtHV9lChoBmgJaA9DCM0jfzBwt2RAlIaUUpRoFU3oA2gWR0CQJzw8nuzAdX2UKGgGaAloD0MIur4PBwmRZUCUhpRSlGgVTegDaBZHQJApSDlHSWt1fZQoaAZoCWgPQwjoS29/Lp5mQJSGlFKUaBVN6ANoFkdAkCnaCg9Ne3V9lChoBmgJaA9DCJc48kDk1mJAlIaUUpRoFU3oA2gWR0CQKihDw6QvdX2UKGgGaAloD0MItmgB2lZfZUCUhpRSlGgVTegDaBZHQJAtB1W8yvd1fZQoaAZoCWgPQwhjCACOvRBlQJSGlFKUaBVN6ANoFkdAkC3TYmLLp3V9lChoBmgJaA9DCOQuwhRlgmVAlIaUUpRoFU3oA2gWR0CQLeBhhH9WdX2UKGgGaAloD0MIjUKSWb0TZ0CUhpRSlGgVTegDaBZHQJAuYIhQm/p1fZQoaAZoCWgPQwhybD1DuGZmQJSGlFKUaBVN6ANoFkdAkDDDdUKiPHV9lChoBmgJaA9DCG+3JAfsAjJAlIaUUpRoFUvGaBZHQJAwzm8ujAV1fZQoaAZoCWgPQwh0tRX7y1deQJSGlFKUaBVN6ANoFkdAkDOQxagVXXV9lChoBmgJaA9DCBvWVBaFgmJAlIaUUpRoFU3oA2gWR0CQOtw4sEq2dX2UKGgGaAloD0MIE3zT9NkWZECUhpRSlGgVTegDaBZHQJA/bZAY51h1fZQoaAZoCWgPQwhwtrkxPe5jQJSGlFKUaBVN6ANoFkdAkECKDwpe/3V9lChoBmgJaA9DCLeb4Jumv15AlIaUUpRoFU3oA2gWR0CQSU+VC5VfdX2UKGgGaAloD0MIzy10JQIBYkCUhpRSlGgVTegDaBZHQJBpZhCtzS11fZQoaAZoCWgPQwh9IHnn0KJmQJSGlFKUaBVN6ANoFkdAkG7xxtHhCXV9lChoBmgJaA9DCLDkKhY/4mdAlIaUUpRoFU3oA2gWR0CQc2i8nNPhdX2UKGgGaAloD0MIowVoW01MZECUhpRSlGgVTegDaBZHQJBz89W6shh1fZQoaAZoCWgPQwj9vn/z4tRkQJSGlFKUaBVN6ANoFkdAkHRB8lXzUnV9lChoBmgJaA9DCLX9KyvNu2NAlIaUUpRoFU3oA2gWR0CQdxU/OdGzdX2UKGgGaAloD0MIS8tIvaecX0CUhpRSlGgVTegDaBZHQJB34pLEk0J1fZQoaAZoCWgPQwgSvCGNipFmQJSGlFKUaBVN6ANoFkdAkHfv+S8rZ3V9lChoBmgJaA9DCI6u0t11fGVAlIaUUpRoFU3oA2gWR0CQeG25QP7OdX2UKGgGaAloD0MIswjFVtCaZkCUhpRSlGgVTegDaBZHQJB686vJRwZ1fZQoaAZoCWgPQwh3u16aouRiQJSGlFKUaBVN6ANoFkdAkHsBbbDdg3V9lChoBmgJaA9DCMdim1Q0AGJAlIaUUpRoFU3oA2gWR0CQfZmseXAudX2UKGgGaAloD0MIm+Wy0TltQ0CUhpRSlGgVS/1oFkdAkILUS/TLGXV9lChoBmgJaA9DCEHYKVaNXGRAlIaUUpRoFU3oA2gWR0CQhJ5VOsT4dX2UKGgGaAloD0MIqI/AH341ZECUhpRSlGgVTegDaBZHQJCI6vV3EAJ1fZQoaAZoCWgPQwiRtvEnqqhmQJSGlFKUaBVN6ANoFkdAkIn+E/Spi3V9lChoBmgJaA9DCNhHp678zmVAlIaUUpRoFU3oA2gWR0CQkkjsD4gzdX2UKGgGaAloD0MItMh2vp+5UUCUhpRSlGgVS+9oFkdAkKrpP2wmmnV9lChoBmgJaA9DCGbbaWtEgmdAlIaUUpRoFU3oA2gWR0CQsmV+Zw4sdX2UKGgGaAloD0MI0sQ7wBP/ZUCUhpRSlGgVTegDaBZHQJC4PsolUqB1fZQoaAZoCWgPQwiWPnRB/SNlQJSGlFKUaBVN6ANoFkdAkL0IyO7xu3V9lChoBmgJaA9DCL6ghQSMymRAlIaUUpRoFU3oA2gWR0CQvaY4Qz1sdX2UKGgGaAloD0MILPNWXYfBY0CUhpRSlGgVTegDaBZHQJC9/PeHi3p1fZQoaAZoCWgPQwiYp3NFKXNGQJSGlFKUaBVLz2gWR0CQvxjoIOYqdX2UKGgGaAloD0MIU3jQ7LrUZkCUhpRSlGgVTegDaBZHQJDA/2saKk51fZQoaAZoCWgPQwgQkgVMYApmQJSGlFKUaBVN6ANoFkdAkMHaujh1knV9lChoBmgJaA9DCI//AkGA2WRAlIaUUpRoFU3oA2gWR0CQwmtoi9qUdX2UKGgGaAloD0MIl6lJ8IYWYECUhpRSlGgVTegDaBZHQJDFBaQmu1Z1fZQoaAZoCWgPQwgT9Bd6RAZkQJSGlFKUaBVN6ANoFkdAkMUTot+TeXV9lChoBmgJaA9DCOdxGMxf90pAlIaUUpRoFUvcaBZHQJDH9kJ8fFJ1fZQoaAZoCWgPQwgK8x5nmvdnQJSGlFKUaBVN6ANoFkdAkMf2jbi6x3V9lChoBmgJaA9DCCJt409UEj9AlIaUUpRoFUvGaBZHQJDKlx7zCk51fZQoaAZoCWgPQwiwARHiSnBjQJSGlFKUaBVN6ANoFkdAkM01ZgXuV3V9lChoBmgJaA9DCMbBpWPO8V1AlIaUUpRoFU3oA2gWR0CQztn3+MqCdX2UKGgGaAloD0MIkl7U7tcfYUCUhpRSlGgVTegDaBZHQJDSve9Ba9t1fZQoaAZoCWgPQwgwLlVpi6ldQJSGlFKUaBVN6ANoFkdAkNwYLThHb3V9lChoBmgJaA9DCJTcYRMZpGJAlIaUUpRoFU3oA2gWR0CQ9M41gpjMdX2UKGgGaAloD0MIeUDZlCttUECUhpRSlGgVS8poFkdAkPtjujRD1HV9lChoBmgJaA9DCIszhjnBFGRAlIaUUpRoFU3oA2gWR0CRAhWN3np0dX2UKGgGaAloD0MIjsni/iMZYUCUhpRSlGgVTegDaBZHQJEG4x0uDjB1fZQoaAZoCWgPQwi13QTftHpnQJSGlFKUaBVN6ANoFkdAkQfR3NcGDHV9lChoBmgJaA9DCLSs+8dCM2JAlIaUUpRoFU3oA2gWR0CRCQm65Gz9dX2UKGgGaAloD0MIdvpBXaQxZ0CUhpRSlGgVTegDaBZHQJELDf1pTMt1fZQoaAZoCWgPQwiGG/D5Ya1nQJSGlFKUaBVN6ANoFkdAkQyN4VymynV9lChoBmgJaA9DCLlRZK2h2WVAlIaUUpRoFU3oA2gWR0CRD4+az/p/dX2UKGgGaAloD0MIrADfbV7WZ0CUhpRSlGgVTegDaBZHQJEPnSRbKRx1fZQoaAZoCWgPQwhhGRu62TxkQJSGlFKUaBVN6ANoFkdAkRLI6XBxgnV9lChoBmgJaA9DCLwi+N9K7mVAlIaUUpRoFU3oA2gWR0CREss2NvOydX2UKGgGaAloD0MI3Lqbp7rMY0CUhpRSlGgVTegDaBZHQJEVWuLaVUx1fZQoaAZoCWgPQwh15h4Svg9iQJSGlFKUaBVN6ANoFkdAkRfjZYgaFXV9lChoBmgJaA9DCJjg1AeSymRAlIaUUpRoFU3oA2gWR0CRGYvDgqEwdX2UKGgGaAloD0MI9FKxMa/dYkCUhpRSlGgVTegDaBZHQJEdTbwjMV11fZQoaAZoCWgPQwi8BRIUP11lQJSGlFKUaBVN6ANoFkdAkT2m9g4OtnV9lChoBmgJaA9DCFvri4Q24WZAlIaUUpRoFU3oA2gWR0CRQ44FzMibdX2UKGgGaAloD0MInBcnvtrGZUCUhpRSlGgVTegDaBZHQJFJIJWvKU51fZQoaAZoCWgPQwhzoIfaNlFkQJSGlFKUaBVN6ANoFkdAkU1QlWwNb3V9lChoBmgJaA9DCONUa2GWb2FAlIaUUpRoFU3oA2gWR0CRTi5q/M4cdX2UKGgGaAloD0MIqoB7nj9eYUCUhpRSlGgVTegDaBZHQJFPSpda+vh1fZQoaAZoCWgPQwimnZrLDfphQJSGlFKUaBVN6ANoFkdAkVErQswta3V9lChoBmgJaA9DCB4aFqMuhmRAlIaUUpRoFU3oA2gWR0CRUqEF4cFRdX2UKGgGaAloD0MIvw8HCVEdZkCUhpRSlGgVTegDaBZHQJFVdvitJWh1fZQoaAZoCWgPQwgsuvWaHmBgQJSGlFKUaBVN6ANoFkdAkVWEsFt8/nV9lChoBmgJaA9DCC0FpP0PH2JAlIaUUpRoFU3oA2gWR0CRWIVDrqt6dX2UKGgGaAloD0MIWONsOoIwYUCUhpRSlGgVTegDaBZHQJFYhfa6BiF1fZQoaAZoCWgPQwiKBil4CgNkQJSGlFKUaBVN6ANoFkdAkVsWf029+XV9lChoBmgJaA9DCLZHb7iPb2ZAlIaUUpRoFU3oA2gWR0CRXX6Ww/xEdX2UKGgGaAloD0MINstlo/P7ZECUhpRSlGgVTegDaBZHQJFfHRNRFZx1fZQoaAZoCWgPQwgz/RLx1sFlQJSGlFKUaBVN6ANoFkdAkWLAAdXDFnV9lChoBmgJaA9DCMJR8uocvGZAlIaUUpRoFU3oA2gWR0CRcRnCO3lTdWUu"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
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 sha256:79b1a60a852257b95ac42170385949f3999a4b6a7678c4112bbec76ec98d7d8c
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c32491192dee4c9e8d844138a1fde59f8ede07710da47a9ce07e5e55836eb47c
|
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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (220 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 263.3444429886375, "std_reward": 24.61662500570924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T21:23:28.248514"}
|