Upload PPO MountainCar-v0 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- ppo-MountainCar-v0.zip +3 -0
- ppo-MountainCar-v0/_stable_baselines3_version +1 -0
- ppo-MountainCar-v0/data +91 -0
- ppo-MountainCar-v0/policy.optimizer.pth +3 -0
- ppo-MountainCar-v0/policy.pth +3 -0
- ppo-MountainCar-v0/pytorch_variables.pth +3 -0
- ppo-MountainCar-v0/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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- MountainCar-v0
|
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: -99.80 +/- 5.10
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: MountainCar-v0
|
20 |
+
type: MountainCar-v0
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **MountainCar-v0**
|
24 |
+
This is a trained model of a **PPO** agent playing **MountainCar-v0** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
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 0x7f4ee757aa70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4ee757ab00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4ee757ab90>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4ee757ac20>", "_build": "<function ActorCriticPolicy._build at 0x7f4ee757acb0>", "forward": "<function ActorCriticPolicy.forward at 0x7f4ee757ad40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4ee757add0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4ee757ae60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4ee757aef0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4ee757af80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4ee7580050>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f4ee75b6e10>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "_shape": [2], "low": "[-1.2 -0.07]", "high": "[0.6 0.07]", "bounded_below": "[ True True]", "bounded_above": "[ True True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "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", "n": 3, "_shape": [], "dtype": "int64", "_np_random": "RandomState(MT19937)"}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": 42, "action_noise": null, "start_time": 1652298910.2782938, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": null, "_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": 2480, "n_steps": 1024, "gamma": 0.99, "gae_lambda": 0.8, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 40, "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-MountainCar-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b6a4246b0f08ae57cad62db540a2685b4d186f6fea27592bd8be0b375a1f163
|
3 |
+
size 135078
|
ppo-MountainCar-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-MountainCar-v0/data
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f4ee757aa70>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4ee757ab00>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4ee757ab90>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4ee757ac20>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f4ee757acb0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f4ee757ad40>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4ee757add0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f4ee757ae60>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4ee757aef0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4ee757af80>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4ee7580050>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f4ee75b6e10>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
2
|
29 |
+
],
|
30 |
+
"low": "[-1.2 -0.07]",
|
31 |
+
"high": "[0.6 0.07]",
|
32 |
+
"bounded_below": "[ True True]",
|
33 |
+
"bounded_above": "[ True True]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "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",
|
39 |
+
"n": 3,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": "RandomState(MT19937)"
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": 42,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1652298910.2782938,
|
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": null,
|
58 |
+
"_last_episode_starts": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
61 |
+
},
|
62 |
+
"_last_original_obs": null,
|
63 |
+
"_episode_num": 0,
|
64 |
+
"use_sde": false,
|
65 |
+
"sde_sample_freq": -1,
|
66 |
+
"_current_progress_remaining": -0.015808000000000044,
|
67 |
+
"ep_info_buffer": {
|
68 |
+
":type:": "<class 'collections.deque'>",
|
69 |
+
":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFWAAAAAAACMAWyUS1aMAXSUR0CX8r8n/kvLdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX8vFnZkCndX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX8vu/UONHdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX8v99tuUEdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX8wz7MxGldX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX8w1A7gbZdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX8xQHzH0cdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX8zSncclxdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX8zRsMy8BdX2UKGgGR8BVAAAAAAAAaAdLVGgIR0CX8zXD3ueCdX2UKGgGR8BZQAAAAAAAaAdLZWgIR0CX80fCyhSMdX2UKGgGR8BZQAAAAAAAaAdLZWgIR0CX81AmReTndX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX81Xsw+MZdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX82DwYtQLdX2UKGgGR8BZQAAAAAAAaAdLZWgIR0CX82OSW7e3dX2UKGgGR8BXwAAAAAAAaAdLX2gIR0CX84E8aGYbdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX84i22G7BdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CX85B9Tgl4dX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CX86jzI3irdX2UKGgGR8BVQAAAAAAAaAdLVWgIR0CX87OWSlnAdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX875C4SYgdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX88HMEA5rdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX888stkFwdX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CX89bqyGBXdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX8/bkfcN6dX2UKGgGR8BVQAAAAAAAaAdLVWgIR0CX8/TPSlWPdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX8/f+jua4dX2UKGgGR8BXgAAAAAAAaAdLXmgIR0CX8/9/BnBddX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9AfNA1NydX2UKGgGR8BVgAAAAAAAaAdLVmgIR0CX9CLLpzLfdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9CNFSbYsdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CX9CJU5uIidX2UKGgGR8BWAAAAAAAAaAdLWGgIR0CX9C1kUbkwdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9FAeJYT1dX2UKGgGR8BVgAAAAAAAaAdLVmgIR0CX9FJswco6dX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9GjEehf0dX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9H3mFJxvdX2UKGgGR8BaQAAAAAAAaAdLaWgIR0CX9INmlImPdX2UKGgGR8BYAAAAAAAAaAdLYGgIR0CX9IgU1yeadX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9I8cdYGMdX2UKGgGR8BZQAAAAAAAaAdLZWgIR0CX9K5eqrBCdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9LYBNmDldX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9LVQAMlUdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CX9LsP8Q7LdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9MbItDlYdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9N7j1f3OdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9N9bor4GdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9OA7PppwdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9OtIClrNdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9Q3/xUeddX2UKGgGR8BWwAAAAAAAaAdLW2gIR0CX9Q7CiyprdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9Q5NGmUGdX2UKGgGR8BXAAAAAAAAaAdLXGgIR0CX9TbNKRMfdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CX9TgCwKSgdX2UKGgGR8BYgAAAAAAAaAdLYmgIR0CX9TsBQvYfdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9T98Z1mrdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9WrsByS3dX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CX9XC+10DEdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9XHVPN3XdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9XeHSF4+dX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9YM72cridX2UKGgGR8BWgAAAAAAAaAdLWmgIR0CX9YVDa4+bdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0CX9YoePq9odX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9Z7sfJV9dX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9an+Q2dedX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CX9bGMn7YTdX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CX9bEXLvCudX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9dEW69TQdX2UKGgGR8BVAAAAAAAAaAdLVGgIR0CX9dXUpd8idX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CX9d1UEPlNdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9f6WgOBldX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9gUXYUWVdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CX9g+mWMS9dX2UKGgGR8BVQAAAAAAAaAdLVWgIR0CX9ia/RE4OdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9jFFlTWHdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9jZn+Q2ddX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9j30PH1fdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9k5VOsT4dX2UKGgGR8BVAAAAAAAAaAdLVGgIR0CX9k/lQuVYdX2UKGgGR8BWwAAAAAAAaAdLW2gIR0CX9laKDTScdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9mkd3jdYdX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CX9n9eQdS3dX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9n8l5WzXdX2UKGgGR8BXgAAAAAAAaAdLXmgIR0CX9pmW+oLodX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9p8h9srNdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CX9qXWOIZZdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9tP9UCJXdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9t8ZDRdAdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9vfT1CgLdX2UKGgGR8BnwAAAAAAAaAdLvmgIR0CX9vutOmBOdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9wDqnm7rdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9wfTCtRvdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9w1/Ue+3dX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CX9xv863iJdX2UKGgGR8BVAAAAAAAAaAdLVGgIR0CX9yHmig01dX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX9yFxGUfQdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9yZPEbYLdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CX9zOk+HJtdX2UKGgGR8BVAAAAAAAAaAdLVGgIR0CX9zl18stkdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CX90rIHTqjdWUu"
|
70 |
+
},
|
71 |
+
"ep_success_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
74 |
+
},
|
75 |
+
"_n_updates": 2480,
|
76 |
+
"n_steps": 1024,
|
77 |
+
"gamma": 0.99,
|
78 |
+
"gae_lambda": 0.8,
|
79 |
+
"ent_coef": 0.01,
|
80 |
+
"vf_coef": 0.5,
|
81 |
+
"max_grad_norm": 0.5,
|
82 |
+
"batch_size": 128,
|
83 |
+
"n_epochs": 40,
|
84 |
+
"clip_range": {
|
85 |
+
":type:": "<class 'function'>",
|
86 |
+
":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/ZmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
87 |
+
},
|
88 |
+
"clip_range_vf": null,
|
89 |
+
"normalize_advantage": true,
|
90 |
+
"target_kl": null
|
91 |
+
}
|
ppo-MountainCar-v0/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b95e30f56c76a577a141af627b035d8345f1e0bc374800a56c97faab3dae71f
|
3 |
+
size 78237
|
ppo-MountainCar-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:963733c81e31924c222467402b63ed6ba71a6a32d16945f6a3becbfd6d40067f
|
3 |
+
size 39873
|
ppo-MountainCar-v0/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-MountainCar-v0/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:ab0f9a70ffc73f8888ca518900cf253c5f76f9532ac57c974dc03ad548945d28
|
3 |
+
size 256540
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -99.8, "std_reward": 5.095095681142799, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T20:27:47.633050"}
|