CoreyMorris
commited on
Commit
•
d4c8233
1
Parent(s):
6c97511
experiment 2. checkpoint 1_010_000
Browse files- README.md +1 -1
- args.yml +3 -3
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +19 -19
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: 274.
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 274.40 +/- 18.97
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
args.yml
CHANGED
@@ -50,17 +50,17 @@
|
|
50 |
- - sampler
|
51 |
- tpe
|
52 |
- - save_freq
|
53 |
-
-
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
61 |
- null
|
62 |
- - tensorboard_log
|
63 |
-
- runs/LunarLander-
|
64 |
- - track
|
65 |
- true
|
66 |
- - trained_agent
|
|
|
50 |
- - sampler
|
51 |
- tpe
|
52 |
- - save_freq
|
53 |
+
- 10000
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 2587859772
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
61 |
- null
|
62 |
- - tensorboard_log
|
63 |
+
- runs/LunarLander-v2__ppo__2587859772__1674536198
|
64 |
- - track
|
65 |
- true
|
66 |
- - trained_agent
|
ppo-LunarLander-v2.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:fb79fcdab12324ba22de2e5324739869a2bf16bf153014d7475c4596439486bb
|
3 |
+
size 150362
|
ppo-LunarLander-v2/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_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -43,14 +43,14 @@
|
|
43 |
"_np_random": "RandomState(MT19937)"
|
44 |
},
|
45 |
"n_envs": 1,
|
46 |
-
"num_timesteps":
|
47 |
"_total_timesteps": 1000000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": 0,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
-
"tensorboard_log": "runs/LunarLander-
|
54 |
"lr_schedule": {
|
55 |
":type:": "<class 'function'>",
|
56 |
":serialized:": "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"
|
@@ -64,16 +64,16 @@
|
|
64 |
"_episode_num": 0,
|
65 |
"use_sde": false,
|
66 |
"sde_sample_freq": -1,
|
67 |
-
"_current_progress_remaining":
|
68 |
"ep_info_buffer": {
|
69 |
":type:": "<class 'collections.deque'>",
|
70 |
-
":serialized:": "
|
71 |
},
|
72 |
"ep_success_buffer": {
|
73 |
":type:": "<class 'collections.deque'>",
|
74 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
75 |
},
|
76 |
-
"_n_updates":
|
77 |
"n_steps": 1024,
|
78 |
"gamma": 0.999,
|
79 |
"gae_lambda": 0.98,
|
|
|
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 0x7fb416ce9940>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb416ce99d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb416ce9a60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb416ce9af0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb416ce9b80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb416ce9c10>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb416ce9ca0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb416ce9d30>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb416ce9dc0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb416ce9e50>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb416ce9ee0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb416ce9f70>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7fb416ce66f0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
43 |
"_np_random": "RandomState(MT19937)"
|
44 |
},
|
45 |
"n_envs": 1,
|
46 |
+
"num_timesteps": 1010000,
|
47 |
"_total_timesteps": 1000000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": 0,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1674536206442318020,
|
52 |
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": "runs/LunarLander-v2__ppo__2587859772__1674536198/LunarLander-v2",
|
54 |
"lr_schedule": {
|
55 |
":type:": "<class 'function'>",
|
56 |
":serialized:": "gAWV7wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXi9ob21lL2NvcmV5L2FuYWNvbmRhMy9lbnZzL2hmLXJsL2xpYi9weXRob24zLjgvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuCQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjF4vaG9tZS9jb3JleS9hbmFjb25kYTMvZW52cy9oZi1ybC9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
|
|
64 |
"_episode_num": 0,
|
65 |
"use_sde": false,
|
66 |
"sde_sample_freq": -1,
|
67 |
+
"_current_progress_remaining": 0.0005760000000000209,
|
68 |
"ep_info_buffer": {
|
69 |
":type:": "<class 'collections.deque'>",
|
70 |
+
":serialized:": "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"
|
71 |
},
|
72 |
"ep_success_buffer": {
|
73 |
":type:": "<class 'collections.deque'>",
|
74 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
75 |
},
|
76 |
+
"_n_updates": 484,
|
77 |
"n_steps": 1024,
|
78 |
"gamma": 0.999,
|
79 |
"gae_lambda": 0.98,
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 88057
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:801508204d39bf7dcb7ff3233412167c344c42717be1edfd7bdbd2d43c53289a
|
3 |
size 88057
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43393
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01473c4ccd0f6bb86fb233d9f3ab1692f08e1444cc46d4843f147d65f9d4c3d4
|
3 |
size 43393
|
replay.mp4
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:e7b08f647a02db8b3c86be2b8b2ac4354ccedf7426352337232a92e15e6389de
|
3 |
+
size 185443
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": 274.
|
|
|
1 |
+
{"mean_reward": 274.40450610000005, "std_reward": 18.96753005233237, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-24T01:15:27.148114"}
|
train_eval_metrics.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:f0e83039644a6f6388468c54e7960f1468459c6ad482d6972b3c6767859dc33a
|
3 |
+
size 107166
|