aljdkaekaa
commited on
Commit
•
f3a2498
1
Parent(s):
b8793a7
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: 165.65 +/- 21.36
|
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 0x7f9f89ef80e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9f89ef8170>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9f89ef8200>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9f89ef8290>", "_build": "<function ActorCriticPolicy._build at 0x7f9f89ef8320>", "forward": "<function ActorCriticPolicy.forward at 0x7f9f89ef83b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9f89ef8440>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9f89ef84d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9f89ef8560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9f89ef85f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9f89ef8680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f9f89f44660>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1668134163936860682, "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": 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-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "False", "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 sha256:2f9692b0724a240123505a4ac3cc3371ac237e0191affe06a9b63793730783a2
|
3 |
+
size 146703
|
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 0x7f9f89ef80e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9f89ef8170>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9f89ef8200>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9f89ef8290>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9f89ef8320>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9f89ef83b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9f89ef8440>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9f89ef84d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9f89ef8560>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9f89ef85f0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9f89ef8680>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f9f89f44660>"
|
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": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1668134163936860682,
|
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:": "gAWVfhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIsDkHz4TiM0CUhpRSlIwBbJRN6AOMAXSUR0CAcED9wWFfdX2UKGgGaAloD0MI3zXoS2+gVECUhpRSlGgVTegDaBZHQIBxcornTy91fZQoaAZoCWgPQwh2jCsujuxDQJSGlFKUaBVN6ANoFkdAgHlhGYrrgXV9lChoBmgJaA9DCNfCLLRzIjvAlIaUUpRoFU1cAWgWR0CAfy5FPSDzdX2UKGgGaAloD0MILo81I4NMEsCUhpRSlGgVS6toFkdAgIJ1Z9uxbHV9lChoBmgJaA9DCCV5ru/DbVZAlIaUUpRoFU3oA2gWR0CAhnBN21UmdX2UKGgGaAloD0MIhZSfVPuFWkCUhpRSlGgVTegDaBZHQICNjx3FDOV1fZQoaAZoCWgPQwjeADPfwS9KQJSGlFKUaBVN6ANoFkdAgJIYoZydWnV9lChoBmgJaA9DCIL/rWTHMVNAlIaUUpRoFU3oA2gWR0CAtpaZhKDkdX2UKGgGaAloD0MINnSzP1AcQECUhpRSlGgVTegDaBZHQIC6OQbMott1fZQoaAZoCWgPQwgz4Cwly+1dQJSGlFKUaBVN6ANoFkdAgL/OvMbFTHV9lChoBmgJaA9DCIfD0sCPUF1AlIaUUpRoFU3oA2gWR0CAwLyuIRAbdX2UKGgGaAloD0MI4ZaPpCRaYkCUhpRSlGgVTegDaBZHQIDNqyt3fQ91fZQoaAZoCWgPQwgydVd2QU1gQJSGlFKUaBVN6ANoFkdAgOes5wOvuHV9lChoBmgJaA9DCCIZcmw9AGBAlIaUUpRoFU3oA2gWR0CA8ZEd/8VIdX2UKGgGaAloD0MIg6YlVkaJWECUhpRSlGgVTegDaBZHQID2OaH9FWp1fZQoaAZoCWgPQwiEZAETuN9jQJSGlFKUaBVN6ANoFkdAgPbSlWOp9HV9lChoBmgJaA9DCK+XpghwkVtAlIaUUpRoFU3oA2gWR0CBAHRm9QGfdX2UKGgGaAloD0MIDtsWZTYBXkCUhpRSlGgVTegDaBZHQIEJbGtITXd1fZQoaAZoCWgPQwhPkq6ZfFpdQJSGlFKUaBVN6ANoFkdAgQ/35WRzR3V9lChoBmgJaA9DCGQgzy7fflpAlIaUUpRoFU3oA2gWR0CBE64J/oaDdX2UKGgGaAloD0MI4dOcvEiPYECUhpRSlGgVTegDaBZHQIEXntF8XvZ1fZQoaAZoCWgPQwgrNXugFbpTQJSGlFKUaBVN6ANoFkdAgR7s6ij+JnV9lChoBmgJaA9DCKK3eHhPnWFAlIaUUpRoFU3oA2gWR0CBI2//NqxkdX2UKGgGaAloD0MIqfdUTnu6PUCUhpRSlGgVTSUBaBZHQIEqvsolUqB1fZQoaAZoCWgPQwibHhSUothjQJSGlFKUaBVN6ANoFkdAgUa5AIIF/3V9lChoBmgJaA9DCBVypZ4F9VZAlIaUUpRoFU3oA2gWR0CBSgfmLcbjdX2UKGgGaAloD0MI8N5RY0IcJ8CUhpRSlGgVTQ8BaBZHQIFNLxLCemN1fZQoaAZoCWgPQwhgcw6eCZBVQJSGlFKUaBVN6ANoFkdAgU8Ywh4dIXV9lChoBmgJaA9DCL1w58JILGFAlIaUUpRoFU3oA2gWR0CBT+x33YcvdX2UKGgGaAloD0MI5zqNtFSAS0CUhpRSlGgVTegDaBZHQIFbZ6D5CWx1fZQoaAZoCWgPQwh88UV7PLpgQJSGlFKUaBVN6ANoFkdAgWAHqNZNf3V9lChoBmgJaA9DCKaaWUsBr0hAlIaUUpRoFUviaBZHQIF8LFAE+xJ1fZQoaAZoCWgPQwiOsKiIU7JgQJSGlFKUaBVN6ANoFkdAgX23rt3OfXV9lChoBmgJaA9DCETf3coS2VpAlIaUUpRoFU3oA2gWR0CBgb+9alk6dX2UKGgGaAloD0MIaaon84+EXUCUhpRSlGgVTegDaBZHQIGCVbu+h5B1fZQoaAZoCWgPQwjayHVTSrViQJSGlFKUaBVN6ANoFkdAgYtjNhVlw3V9lChoBmgJaA9DCIdqSrIOo0FAlIaUUpRoFUv+aBZHQIGRzgOz6ad1fZQoaAZoCWgPQwgWo6619yRfQJSGlFKUaBVN6ANoFkdAgZsAA6uGK3V9lChoBmgJaA9DCHS1FfvL6V9AlIaUUpRoFU3oA2gWR0CBny+cH4XXdX2UKGgGaAloD0MI6xnCMUsVYECUhpRSlGgVTegDaBZHQIGjmdoWYWt1fZQoaAZoCWgPQwjVJHhDGotFQJSGlFKUaBVNOwFoFkdAgafPUaya/nV9lChoBmgJaA9DCPWB5J1D9U5AlIaUUpRoFU3oA2gWR0CBq2274BV/dX2UKGgGaAloD0MIcNHJUusGYECUhpRSlGgVTegDaBZHQIGwempEQXh1fZQoaAZoCWgPQwjvcaYJW7VgQJSGlFKUaBVN6ANoFkdAgdq+IVM233V9lChoBmgJaA9DCDHuBtFa1VVAlIaUUpRoFU3oA2gWR0CB3o9Oh0yQdX2UKGgGaAloD0MIHOxNDMltYECUhpRSlGgVTegDaBZHQIHkjlYEGJN1fZQoaAZoCWgPQwi22O2zyoRfQJSGlFKUaBVN6ANoFkdAgeWd/BnBcnV9lChoBmgJaA9DCB2SWiiZe1pAlIaUUpRoFU3oA2gWR0CB8txIatLddX2UKGgGaAloD0MIFcWrrG0/VkCUhpRSlGgVTegDaBZHQIIVRKpT/AF1fZQoaAZoCWgPQwhW73A7NKwmwJSGlFKUaBVN6ANoFkdAghcJ/oaDPHV9lChoBmgJaA9DCF7b2y3Jp1hAlIaUUpRoFU3oA2gWR0CCHDZmqYJFdX2UKGgGaAloD0MIB9MwfETqXUCUhpRSlGgVTegDaBZHQIImd/axoqV1fZQoaAZoCWgPQwixiGGHMXFJQJSGlFKUaBVN6ANoFkdAgi2ilJpWWHV9lChoBmgJaA9DCI9srprnEldAlIaUUpRoFU3oA2gWR0CCN2wlByCGdX2UKGgGaAloD0MIyNPyA1fpFECUhpRSlGgVTRYBaBZHQII5T1ZkkKN1fZQoaAZoCWgPQwgGY0Si0MhdQJSGlFKUaBVN6ANoFkdAgjt3aSLZSXV9lChoBmgJaA9DCHl1jgHZKGNAlIaUUpRoFU3oA2gWR0CCP5s2NvOydX2UKGgGaAloD0MIe7yQDg9qXUCUhpRSlGgVTegDaBZHQIJDlo6CDmN1fZQoaAZoCWgPQwjUK2UZ4hxhQJSGlFKUaBVN6ANoFkdAgkcfPw/gSHV9lChoBmgJaA9DCFzK+WLvElFAlIaUUpRoFU3oA2gWR0CCS9L5AQg+dX2UKGgGaAloD0MIEhPU8C1TXUCUhpRSlGgVTegDaBZHQIJzOukk8ih1fZQoaAZoCWgPQwj1S8Rb571aQJSGlFKUaBVN6ANoFkdAgncIg3cYZXV9lChoBmgJaA9DCFD/WfPjjlNAlIaUUpRoFU3oA2gWR0CCfOGIKtxNdX2UKGgGaAloD0MIur963Le7YUCUhpRSlGgVTegDaBZHQIJ92wqy4Wl1fZQoaAZoCWgPQwh72uGvydZeQJSGlFKUaBVN6ANoFkdAgosQJXyRS3V9lChoBmgJaA9DCLOVl/xPHWFAlIaUUpRoFU3oA2gWR0CCr9e7cwg1dX2UKGgGaAloD0MIYymSrwTZVECUhpRSlGgVTegDaBZHQIK1jwhGH591fZQoaAZoCWgPQwi0AG2rWa8lwJSGlFKUaBVNSAFoFkdAgrjXjMmnfnV9lChoBmgJaA9DCAHg2LPnLVxAlIaUUpRoFU3oA2gWR0CCwMCXhOxjdX2UKGgGaAloD0MIEt2zrtHPV0CUhpRSlGgVTegDaBZHQILImetjkMl1fZQoaAZoCWgPQwgTu7a3W8pLQJSGlFKUaBVN6ANoFkdAgtNxIatLc3V9lChoBmgJaA9DCHkkXp7OglhAlIaUUpRoFU3oA2gWR0CC1bGlyimEdX2UKGgGaAloD0MIOLwgIjUMUECUhpRSlGgVTegDaBZHQILYJU5uIh11fZQoaAZoCWgPQwj+1HjpJpBcQJSGlFKUaBVN6ANoFkdAgt0BjnV5KXV9lChoBmgJaA9DCEUPfAxWu1BAlIaUUpRoFU3oA2gWR0CC4a7r9l3AdX2UKGgGaAloD0MI5Q6byMxPWkCUhpRSlGgVTegDaBZHQILlhqTKT0R1fZQoaAZoCWgPQwha8Q2Fz6BXQJSGlFKUaBVN6ANoFkdAgupTx5LRKHV9lChoBmgJaA9DCNLI5xVPrWBAlIaUUpRoFU3oA2gWR0CDFDFKkEcLdX2UKGgGaAloD0MIe7/Rjht4XUCUhpRSlGgVTegDaBZHQIMee9cry2B1fZQoaAZoCWgPQwgD0ZMyqapcQJSGlFKUaBVN6ANoFkdAgx+UJv5xi3V9lChoBmgJaA9DCPq3y37dz2BAlIaUUpRoFU3oA2gWR0CDLoObRWtEdX2UKGgGaAloD0MIIApmTMHVWkCUhpRSlGgVTegDaBZHQIM/4m1IAfd1fZQoaAZoCWgPQwjQDriumBtfQJSGlFKUaBVN6ANoFkdAg1qqREF4cHV9lChoBmgJaA9DCG2rWWf82WJAlIaUUpRoFU3oA2gWR0CDXkAOrhitdX2UKGgGaAloD0MIhleSPNcPM8CUhpRSlGgVTTYBaBZHQINiPwqiGnJ1fZQoaAZoCWgPQwj/P06YMPBZQJSGlFKUaBVN6ANoFkdAg2YwevIOpnV9lChoBmgJaA9DCErx8QnZM1RAlIaUUpRoFU3oA2gWR0CDbWXEZR8/dX2UKGgGaAloD0MICwvuBzwhVECUhpRSlGgVTegDaBZHQIN3Evh60IF1fZQoaAZoCWgPQwjQm4pUGABTQJSGlFKUaBVN6ANoFkdAg3jhS1mapnV9lChoBmgJaA9DCLrZHyi3PF1AlIaUUpRoFU3oA2gWR0CDeuEeQuEmdX2UKGgGaAloD0MISMSUSKI3W0CUhpRSlGgVTegDaBZHQIN+vZGrjo91fZQoaAZoCWgPQwiaC1weazNfQJSGlFKUaBVN6ANoFkdAg4JqgAZKnXV9lChoBmgJaA9DCKXbErngcFpAlIaUUpRoFU3oA2gWR0CDhXAeq7yydX2UKGgGaAloD0MIHO+OjNU/XECUhpRSlGgVTegDaBZHQIOJtOEdvKl1fZQoaAZoCWgPQwj+1HjpJpZdQJSGlFKUaBVN6ANoFkdAg7HVu76HkHV9lChoBmgJaA9DCJ3Ul6Ud3WBAlIaUUpRoFU3oA2gWR0CDvJlhgE2YdX2UKGgGaAloD0MIKo4Dr5btWkCUhpRSlGgVTegDaBZHQIPO3xQSBbx1fZQoaAZoCWgPQwgzUBn/PkdfQJSGlFKUaBVN6ANoFkdAg+KLzwtrbnV9lChoBmgJaA9DCGlyMQbWcQ1AlIaUUpRoFU0/AWgWR0CD585DJEH/dWUu"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
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:bc3aa567a1e3ded6bfb402b1235797bd686b327c19346e4ae1e10b8db447eeeb
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f48e4010422c35a7b4d6d399eb30f930b4a248c638bfddf128dcacc2fb511a4
|
3 |
+
size 43073
|
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-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.7.15
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.12.1+cu113
|
5 |
+
GPU Enabled: False
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (248 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 165.64517461362638, "std_reward": 21.364026333572046, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-11T03:03:28.814023"}
|