Upload PPO LunarLander-v2 trained agent
Browse files- README.md +16 -40
- config.json +1 -1
- ppo_lunar_landar.zip +2 -2
- ppo_lunar_landar/_stable_baselines3_version +1 -1
- ppo_lunar_landar/data +17 -17
- ppo_lunar_landar/policy.optimizer.pth +1 -1
- ppo_lunar_landar/policy.pth +2 -2
- ppo_lunar_landar/system_info.txt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- LunarLander-v2
|
4 |
-
- ppo
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
-
-
|
8 |
-
- deep-rl-course
|
9 |
model-index:
|
10 |
- name: PPO
|
11 |
results:
|
@@ -17,45 +16,22 @@ model-index:
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
-
value:
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
24 |
|
25 |
-
|
|
|
|
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
'wandb_entity': None
|
38 |
-
'capture_video': False
|
39 |
-
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps': 10000000
|
41 |
-
'learning_rate': 2.5e-05
|
42 |
-
'num_envs': 8
|
43 |
-
'num_steps': 2048
|
44 |
-
'anneal_lr': True
|
45 |
-
'gae': True
|
46 |
-
'gamma': 0.999
|
47 |
-
'gae_lambda': 0.98
|
48 |
-
'num_minibatches': 512
|
49 |
-
'update_epochs': 4
|
50 |
-
'norm_adv': True
|
51 |
-
'clip_coef': 0.2
|
52 |
-
'clip_vloss': True
|
53 |
-
'ent_coef': 0.01
|
54 |
-
'vf_coef': 0.5
|
55 |
-
'max_grad_norm': 0.5
|
56 |
-
'target_kl': None
|
57 |
-
'repo_id': 'zzen0008/ppo-LunarLander-v2'
|
58 |
-
'batch_size': 16384
|
59 |
-
'minibatch_size': 32}
|
60 |
-
```
|
61 |
-
|
|
|
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:
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 245.52 +/- 21.29
|
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
CHANGED
@@ -1 +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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f89736b5af0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f89736b5b80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f89736b5c10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f89736b5ca0>", "_build": "<function ActorCriticPolicy._build at 0x7f89736b5d30>", "forward": "<function ActorCriticPolicy.forward at 0x7f89736b5dc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f89736b5e50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f89736b5ee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f89736b5f70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f89736b8040>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f89736b80d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f89736b8160>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f89736b65c0>"}, "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": 1678250480051653327, "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-5.10.0-20-amd64-x86_64-with-glibc2.31 # 1 SMP Debian 5.10.158-2 (2022-12-13)", "Python": "3.9.14", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fab2ad75af0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fab2ad75b80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fab2ad75c10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fab2ad75ca0>", "_build": "<function ActorCriticPolicy._build at 0x7fab2ad75d30>", "forward": "<function ActorCriticPolicy.forward at 0x7fab2ad75dc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fab2ad75e50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fab2ad75ee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fab2ad75f70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fab2ad79040>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fab2ad790d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fab2ad79160>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fab2ad76900>"}, "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": 1678651856726034995, "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": 128, "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-5.10.0-20-amd64-x86_64-with-glibc2.31 # 1 SMP Debian 5.10.158-2 (2022-12-13)", "Python": "3.9.14", "Stable-Baselines3": "1.8.0a2", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
|
ppo_lunar_landar.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:864343ed968ada417c6f063b4615455a9a0bb2505c6ea1e603a526d565c4d79c
|
3 |
+
size 147442
|
ppo_lunar_landar/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
1.
|
|
|
1 |
+
1.8.0a2
|
ppo_lunar_landar/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -48,7 +48,7 @@
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -70,7 +70,7 @@
|
|
70 |
"_current_progress_remaining": -0.015808000000000044,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
@@ -83,7 +83,7 @@
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fab2ad75af0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fab2ad75b80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fab2ad75c10>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fab2ad75ca0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fab2ad75d30>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fab2ad75dc0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fab2ad75e50>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fab2ad75ee0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fab2ad75f70>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fab2ad79040>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fab2ad790d0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fab2ad79160>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fab2ad76900>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1678651856726034995,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAGbLRj17spO6h74NuUZcvbUrLJO6W78kOAAAgD8AAIA/zbUFPVwPFbqq6W68pjPdNsb8DrtCb0u2AACAPwAAgD8zUUG8e8SEut40PLw/iYy1x4suu27h+TQAAIA/AACAP82+M76o2rY/iRkCv/2EqL4kj2G+UwIevgAAAAAAAAAADWmjPeFQkbr4RrM4k4fxNYiHJDpjodG3AACAPwAAgD+aR9a8H63OueqI6zpFIFk2z4BKO59eC7oAAIA/AACAPwBcYL2upY+6K0/hOauheLaRLi26ugACuQAAgD8AAIA/s05FPSoMID/10tY8fPGDvtvVVjzke8E9AAAAAAAAAACNzHc+i7u1Psp8sL1+IzO+lmKGvGoJjT0AAAAAAAAAAJrNrbyGurA/mR4Fvyo0wL6k+2884pWCPAAAAAAAAAAAjSj7vaTmCT/ygfa85kuWvgLbZ72BN4O9AAAAAAAAAADwSnC+7LyKuyZySDu+jJQ4R0ggPRtcdLoAAIA/AACAPwAyYTxcl0e6vrpmu24xz7Mx4jO7ZOo8MwAAgD8AAIA/AKZ5vAmdET16lZ89ISYDvhVQCD3uSXS9AAAAAAAAAABmbYM8j84jukNX6zqaTZezhhcTuo67CboAAIA/AACAP5opj7r2BFm65lD1uKLRoLOjMke7AAoQOAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
70 |
"_current_progress_remaining": -0.015808000000000044,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 128,
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
ppo_lunar_landar/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a964bf5aa5a7930b8479ae095a13451d1d30b13e8c1301873cb2c8dd94c84e15
|
3 |
size 87929
|
ppo_lunar_landar/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5720e67f6c0425762c98923e16f9188b91a93e61b539b17ae45e2258e4166644
|
3 |
+
size 43329
|
ppo_lunar_landar/system_info.txt
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
- OS: Linux-5.10.0-20-amd64-x86_64-with-glibc2.31 # 1 SMP Debian 5.10.158-2 (2022-12-13)
|
2 |
- Python: 3.9.14
|
3 |
-
- Stable-Baselines3: 1.
|
4 |
- PyTorch: 1.13.1+cu117
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.24.2
|
|
|
1 |
- OS: Linux-5.10.0-20-amd64-x86_64-with-glibc2.31 # 1 SMP Debian 5.10.158-2 (2022-12-13)
|
2 |
- Python: 3.9.14
|
3 |
+
- Stable-Baselines3: 1.8.0a2
|
4 |
- PyTorch: 1.13.1+cu117
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.24.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"mean_reward": 245.5205252221114, "std_reward": 21.29322567221237, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-13T07:32:47.598040"}
|