Initial commit
Browse files- README.md +1 -1
- a2c-PandaReachDense-v2.zip +2 -2
- a2c-PandaReachDense-v2/data +14 -14
- a2c-PandaReachDense-v2/policy.optimizer.pth +2 -2
- a2c-PandaReachDense-v2/policy.pth +1 -1
- a2c-PandaReachDense-v2/system_info.txt +4 -4
- config.json +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
- vec_normalize.pkl +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: PandaReachDense-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: PandaReachDense-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -22.40 +/- 7.73
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
a2c-PandaReachDense-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 sha256:3c89e13dccdefbddf22da0147d697d690dc0a4ef23aeb35c6ac84bac3797c86a
|
3 |
+
size 103755
|
a2c-PandaReachDense-v2/data
CHANGED
@@ -4,9 +4,9 @@
|
|
4 |
":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at
|
8 |
"__abstractmethods__": "frozenset()",
|
9 |
-
"_abc_impl": "<
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {
|
@@ -19,24 +19,24 @@
|
|
19 |
"weight_decay": 0
|
20 |
}
|
21 |
},
|
22 |
-
"num_timesteps":
|
23 |
-
"_total_timesteps":
|
24 |
"_num_timesteps_at_start": 0,
|
25 |
"seed": null,
|
26 |
"action_noise": null,
|
27 |
-
"start_time":
|
28 |
"learning_rate": 0.0007,
|
29 |
"tensorboard_log": null,
|
30 |
"lr_schedule": {
|
31 |
":type:": "<class 'function'>",
|
32 |
-
":serialized:": "
|
33 |
},
|
34 |
"_last_obs": {
|
35 |
":type:": "<class 'collections.OrderedDict'>",
|
36 |
-
":serialized:": "
|
37 |
-
"achieved_goal": "[[0.
|
38 |
-
"desired_goal": "[[-0.
|
39 |
-
"observation": "[[0.
|
40 |
},
|
41 |
"_last_episode_starts": {
|
42 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -44,9 +44,9 @@
|
|
44 |
},
|
45 |
"_last_original_obs": {
|
46 |
":type:": "<class 'collections.OrderedDict'>",
|
47 |
-
":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAA6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
48 |
"achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
|
49 |
-
"desired_goal": "[[
|
50 |
"observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
|
51 |
},
|
52 |
"_episode_num": 0,
|
@@ -56,13 +56,13 @@
|
|
56 |
"_stats_window_size": 100,
|
57 |
"ep_info_buffer": {
|
58 |
":type:": "<class 'collections.deque'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"ep_success_buffer": {
|
62 |
":type:": "<class 'collections.deque'>",
|
63 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
64 |
},
|
65 |
-
"_n_updates":
|
66 |
"n_steps": 5,
|
67 |
"gamma": 0.99,
|
68 |
"gae_lambda": 1.0,
|
|
|
4 |
":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7fa63c4d0a60>",
|
8 |
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc_data object at 0x7fa63c4bfd50>"
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {
|
|
|
19 |
"weight_decay": 0
|
20 |
}
|
21 |
},
|
22 |
+
"num_timesteps": 1000,
|
23 |
+
"_total_timesteps": 1000,
|
24 |
"_num_timesteps_at_start": 0,
|
25 |
"seed": null,
|
26 |
"action_noise": null,
|
27 |
+
"start_time": 1682494446377164262,
|
28 |
"learning_rate": 0.0007,
|
29 |
"tensorboard_log": null,
|
30 |
"lr_schedule": {
|
31 |
":type:": "<class 'function'>",
|
32 |
+
":serialized:": "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"
|
33 |
},
|
34 |
"_last_obs": {
|
35 |
":type:": "<class 'collections.OrderedDict'>",
|
36 |
+
":serialized:": "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",
|
37 |
+
"achieved_goal": "[[ 0.4662246 -0.30622184 0.9402406 ]\n [ 0.4662246 -0.30622184 0.9402406 ]\n [ 0.4662246 -0.30622184 0.9402406 ]\n [ 0.4662246 -0.30622184 0.9402406 ]]",
|
38 |
+
"desired_goal": "[[-0.5481118 1.357561 -0.94315 ]\n [-0.49097213 -0.79237723 -0.52946746]\n [ 0.38113752 -1.6158689 1.7662437 ]\n [-1.6462204 -1.6912585 1.6016108 ]]",
|
39 |
+
"observation": "[[ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]\n [ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]\n [ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]\n [ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]]"
|
40 |
},
|
41 |
"_last_episode_starts": {
|
42 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
44 |
},
|
45 |
"_last_original_obs": {
|
46 |
":type:": "<class 'collections.OrderedDict'>",
|
47 |
+
":serialized:": "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",
|
48 |
"achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
|
49 |
+
"desired_goal": "[[ 0.03209666 -0.07382311 0.22757041]\n [-0.01465617 0.0464931 0.22927874]\n [ 0.02134565 -0.09092695 0.16953704]\n [ 0.00362016 -0.00534372 0.25422063]]",
|
50 |
"observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
|
51 |
},
|
52 |
"_episode_num": 0,
|
|
|
56 |
"_stats_window_size": 100,
|
57 |
"ep_info_buffer": {
|
58 |
":type:": "<class 'collections.deque'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"ep_success_buffer": {
|
62 |
":type:": "<class 'collections.deque'>",
|
63 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
64 |
},
|
65 |
+
"_n_updates": 50,
|
66 |
"n_steps": 5,
|
67 |
"gamma": 0.99,
|
68 |
"gae_lambda": 1.0,
|
a2c-PandaReachDense-v2/policy.optimizer.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 sha256:8e43c31ab508d0ca651ecfc0191c07a1ce019a415d258280a4f572b82bc0da4f
|
3 |
+
size 44670
|
a2c-PandaReachDense-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:941467ac2c044b6383b98e3971701a6be739b26c8c09cc75d0d1465ccb45ced4
|
3 |
size 46014
|
a2c-PandaReachDense-v2/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
- OS: Linux-5.
|
2 |
-
- Python: 3.
|
3 |
- Stable-Baselines3: 1.8.0
|
4 |
-
- PyTorch:
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
- Gym: 0.21.0
|
|
|
1 |
+
- OS: Linux-5.15.0-52-generic-x86_64-with-glibc2.29 # 58~20.04.1-Ubuntu SMP Thu Oct 13 13:09:46 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
- Stable-Baselines3: 1.8.0
|
4 |
+
- PyTorch: 1.12.1
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.4
|
7 |
- Gym: 0.21.0
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7fa090bcae50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa090c3df80>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682431367250194102, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RvAGjbi6x4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[0.40388653 0.01075965 0.56231296]\n [0.40388653 0.01075965 0.56231296]\n [0.40388653 0.01075965 0.56231296]\n [0.40388653 0.01075965 0.56231296]]", "desired_goal": "[[-0.12619619 0.9497615 -0.4996053 ]\n [-0.5793722 -0.19004203 -0.5828679 ]\n [ 1.7161498 -1.2493079 -1.6316088 ]\n [-1.6727755 -1.3036445 -0.42759433]]", "observation": "[[0.40388653 0.01075965 0.56231296 0.00233036 0.00326712 0.00279579]\n [0.40388653 0.01075965 0.56231296 0.00233036 0.00326712 0.00279579]\n [0.40388653 0.01075965 0.56231296 0.00233036 0.00326712 0.00279579]\n [0.40388653 0.01075965 0.56231296 0.00233036 0.00326712 0.00279579]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", "desired_goal": "[[-0.04937278 -0.10588694 0.18232252]\n [ 0.05338205 0.10034949 0.13495354]\n [-0.0244446 0.01827885 0.29252276]\n [-0.04679074 -0.06397635 0.15086171]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_np_random": null}, "n_envs": 4, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7fa63c4d0a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fa63c4bfd50>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682494446377164262, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.4662246 -0.30622184 0.9402406 ]\n [ 0.4662246 -0.30622184 0.9402406 ]\n [ 0.4662246 -0.30622184 0.9402406 ]\n [ 0.4662246 -0.30622184 0.9402406 ]]", "desired_goal": "[[-0.5481118 1.357561 -0.94315 ]\n [-0.49097213 -0.79237723 -0.52946746]\n [ 0.38113752 -1.6158689 1.7662437 ]\n [-1.6462204 -1.6912585 1.6016108 ]]", "observation": "[[ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]\n [ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]\n [ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]\n [ 0.4662246 -0.30622184 0.9402406 0.10796438 -0.05316231 0.07094373]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", "desired_goal": "[[ 0.03209666 -0.07382311 0.22757041]\n [-0.01465617 0.0464931 0.22927874]\n [ 0.02134565 -0.09092695 0.16953704]\n [ 0.00362016 -0.00534372 0.25422063]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVbQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLA4WUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaApLA4WUjAFDlHSUUpSMBGhpZ2iUaBIolgwAAAAAAAAAAACAPwAAgD8AAIA/lGgKSwOFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWAwAAAAAAAAABAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYDAAAAAAAAAAEBAZRoIUsDhZRoFXSUUpSMCl9ucF9yYW5kb22UTnViLg==", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_np_random": null}, "n_envs": 4, "system_info": {"OS": "Linux-5.15.0-52-generic-x86_64-with-glibc2.29 # 58~20.04.1-Ubuntu SMP Thu Oct 13 13:09:46 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.8.0", "PyTorch": "1.12.1", "GPU Enabled": "True", "Numpy": "1.23.4", "Gym": "0.21.0"}}
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -22.39945497252047, "std_reward": 7.728387906934784, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T07:34:11.330249"}
|
vec_normalize.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2381
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b7213a8b7e785255bf4a3e3000ce66d2d20f96e74541d573c061fb22102e912
|
3 |
size 2381
|