Initial commit
Browse files- README.md +1 -1
- a2c-PandaPushDense-v2.zip +2 -2
- a2c-PandaPushDense-v2/data +13 -13
- a2c-PandaPushDense-v2/policy.optimizer.pth +1 -1
- a2c-PandaPushDense-v2/policy.pth +1 -1
- config.json +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
type: PandaPushDense-v2
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value: -
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 16 |
type: PandaPushDense-v2
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: -8.31 +/- 3.41
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
a2c-PandaPushDense-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 sha256:5ccaf19d5820c38b498a339e7be1543897285d4be5915f0947fef750c07db70f
|
| 3 |
+
size 117344
|
a2c-PandaPushDense-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": "<_abc._abc_data object at
|
| 10 |
},
|
| 11 |
"verbose": 1,
|
| 12 |
"policy_kwargs": {
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
},
|
| 22 |
"observation_space": {
|
| 23 |
":type:": "<class 'gym.spaces.dict.Dict'>",
|
| 24 |
-
":serialized:": "
|
| 25 |
"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. -10. -10.\n -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10.], (18,), float32))])",
|
| 26 |
"_shape": null,
|
| 27 |
"dtype": null,
|
|
@@ -29,7 +29,7 @@
|
|
| 29 |
},
|
| 30 |
"action_space": {
|
| 31 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 32 |
-
":serialized:": "
|
| 33 |
"dtype": "float32",
|
| 34 |
"_shape": [
|
| 35 |
3
|
|
@@ -46,7 +46,7 @@
|
|
| 46 |
"_num_timesteps_at_start": 0,
|
| 47 |
"seed": null,
|
| 48 |
"action_noise": null,
|
| 49 |
-
"start_time":
|
| 50 |
"learning_rate": 0.0007,
|
| 51 |
"tensorboard_log": null,
|
| 52 |
"lr_schedule": {
|
|
@@ -55,10 +55,10 @@
|
|
| 55 |
},
|
| 56 |
"_last_obs": {
|
| 57 |
":type:": "<class 'collections.OrderedDict'>",
|
| 58 |
-
":serialized:": "
|
| 59 |
-
"achieved_goal": "[[
|
| 60 |
-
"desired_goal": "[[
|
| 61 |
-
"observation": "[[-
|
| 62 |
},
|
| 63 |
"_last_episode_starts": {
|
| 64 |
":type:": "<class 'numpy.ndarray'>",
|
|
@@ -66,10 +66,10 @@
|
|
| 66 |
},
|
| 67 |
"_last_original_obs": {
|
| 68 |
":type:": "<class 'collections.OrderedDict'>",
|
| 69 |
-
":serialized:": "
|
| 70 |
-
"achieved_goal": "[[
|
| 71 |
-
"desired_goal": "[[
|
| 72 |
-
"observation": "[[ 3.
|
| 73 |
},
|
| 74 |
"_episode_num": 0,
|
| 75 |
"use_sde": false,
|
|
|
|
| 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 0x7f5a28c4a5f0>",
|
| 8 |
"__abstractmethods__": "frozenset()",
|
| 9 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f5a28c50580>"
|
| 10 |
},
|
| 11 |
"verbose": 1,
|
| 12 |
"policy_kwargs": {
|
|
|
|
| 21 |
},
|
| 22 |
"observation_space": {
|
| 23 |
":type:": "<class 'gym.spaces.dict.Dict'>",
|
| 24 |
+
":serialized:": "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",
|
| 25 |
"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. -10. -10.\n -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10.], (18,), float32))])",
|
| 26 |
"_shape": null,
|
| 27 |
"dtype": null,
|
|
|
|
| 29 |
},
|
| 30 |
"action_space": {
|
| 31 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 32 |
+
":serialized:": "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",
|
| 33 |
"dtype": "float32",
|
| 34 |
"_shape": [
|
| 35 |
3
|
|
|
|
| 46 |
"_num_timesteps_at_start": 0,
|
| 47 |
"seed": null,
|
| 48 |
"action_noise": null,
|
| 49 |
+
"start_time": 1676810545216914887,
|
| 50 |
"learning_rate": 0.0007,
|
| 51 |
"tensorboard_log": null,
|
| 52 |
"lr_schedule": {
|
|
|
|
| 55 |
},
|
| 56 |
"_last_obs": {
|
| 57 |
":type:": "<class 'collections.OrderedDict'>",
|
| 58 |
+
":serialized:": "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",
|
| 59 |
+
"achieved_goal": "[[ 1.4375114e+00 3.7055409e-01 -8.3448819e-04]\n [ 4.0368223e-01 1.1364377e+00 -8.3448819e-04]\n [-1.1124331e+00 -1.5997032e+00 -8.3448819e-04]\n [-7.2877222e-01 9.2787325e-02 -8.3448819e-04]]",
|
| 60 |
+
"desired_goal": "[[ 1.6787918e+00 -1.7057517e+00 4.0767707e-05]\n [-2.5586367e-01 4.0557161e-01 4.0767707e-05]\n [-9.3583465e-01 4.5362788e-01 4.0767707e-05]\n [-4.8710012e-01 8.4655762e-01 4.0767707e-05]]",
|
| 61 |
+
"observation": "[[-2.2828999e+00 1.8026731e+00 -6.9599640e-01 -2.5590426e-01\n -3.7827924e-01 -4.7194764e-01 1.4375114e+00 3.7055409e-01\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695971e-06\n 2.5336739e-02 -7.8686383e-03]\n [-1.8001274e+00 1.2900239e+00 1.7174590e+00 -6.2497097e-01\n 1.1568509e+00 1.4558060e-01 4.0368223e-01 1.1364377e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695967e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 6.1482060e-01 -1.0674846e-01 -2.2677412e+00 -1.1223067e+00\n 1.6859711e+00 -1.5176313e+00 -1.1124331e+00 -1.5997032e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0696285e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 8.1928092e-01 -2.6075025e+00 -1.4119338e+00 1.7270075e-01\n -7.5215530e-01 3.9653251e-01 -7.2877222e-01 9.2787325e-02\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695976e-06\n 2.5336739e-02 -7.8686383e-03]]"
|
| 62 |
},
|
| 63 |
"_last_episode_starts": {
|
| 64 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
|
| 66 |
},
|
| 67 |
"_last_original_obs": {
|
| 68 |
":type:": "<class 'collections.OrderedDict'>",
|
| 69 |
+
":serialized:": "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",
|
| 70 |
+
"achieved_goal": "[[ 0.11815833 0.07831377 0.02 ]\n [ 0.02371145 0.13088465 0.02 ]\n [-0.11479533 -0.05692631 0.02 ]\n [-0.07974548 0.05924763 0.02 ]]",
|
| 71 |
+
"desired_goal": "[[ 0.09253775 -0.09521101 0.02 ]\n [-0.04829011 0.05066176 0.02 ]\n [-0.0977867 0.053982 0.02 ]\n [-0.06512232 0.08112978 0.02 ]]",
|
| 72 |
+
"observation": "[[ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 1.18158326e-01 7.83137679e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 2.37114523e-02 1.30884647e-01\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -1.14795335e-01 -5.69263138e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -7.97454789e-02 5.92476279e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]]"
|
| 73 |
},
|
| 74 |
"_episode_num": 0,
|
| 75 |
"use_sde": false,
|
a2c-PandaPushDense-v2/policy.optimizer.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50878
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa618d0eb3f327a6e3b54c997846dcb1bafd74a65b7739588c9f169ef40566e9
|
| 3 |
size 50878
|
a2c-PandaPushDense-v2/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 52158
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b1610509fd05d7456615282f102202827c2b03d0058e6c7bca6871deb74c9df
|
| 3 |
size 52158
|
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 0x7f0a2a3325f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0a2a33c640>"}, "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}}, "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. -10. -10.\n -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10.], (18,), 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, "num_timesteps": 20, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676810099835003107, "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": "[[-1.2268063e+00 6.4080411e-01 -8.3448819e-04]\n [ 1.1228409e+00 -1.6346854e+00 -8.3448819e-04]\n [ 8.3536750e-01 9.5580584e-01 -8.3448819e-04]\n [-7.3140991e-01 3.8127221e-02 -8.3448819e-04]]", "desired_goal": "[[ 7.2193575e-01 -9.2012525e-02 4.0767707e-05]\n [-4.9567774e-01 -1.3526119e+00 4.0767707e-05]\n [ 1.1464348e+00 1.4679189e+00 4.0767707e-05]\n [-1.3727673e+00 -2.3281092e-02 4.0767707e-05]]", "observation": "[[-1.8333431e+00 -1.2844002e+00 6.6924912e-01 4.5910752e-01\n 7.0849970e-02 1.4441338e+00 -1.2268063e+00 6.4080411e-01\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695744e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 1.1067957e+00 -5.9119064e-01 2.7893198e-01 -2.1979967e-01\n -3.4195054e-01 -1.6458657e-01 1.1228409e+00 -1.6346854e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695739e-06\n 2.5336739e-02 -7.8686383e-03]\n [-5.5689818e-01 -1.3962218e+00 -1.6724229e+00 -1.4485761e+00\n -1.1220379e+00 -1.2155876e+00 8.3536750e-01 9.5580584e-01\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695744e-06\n 2.5336739e-02 -7.8686383e-03]\n [-2.0165567e+00 2.0975673e+00 -3.1495483e+00 -8.2419676e-01\n -7.8383875e-01 -8.4392267e-01 -7.3140991e-01 3.8127221e-02\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695744e-06\n 2.5336739e-02 -7.8686383e-03]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.13451874 0.06886772 0.02 ]\n [ 0.1228848 -0.13070515 0.02 ]\n [ 0.09139212 0.09649509 0.02 ]\n [-0.08024815 0.01600966 0.02 ]]", "desired_goal": "[[-0.08347423 0.03542688 0.02 ]\n [-0.11046871 -0.02774564 0.02 ]\n [-0.07406309 0.11359984 0.02 ]\n [-0.12991378 0.03887122 0.02 ]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 -1.3451874e-01 6.8867721e-02\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 1.2288480e-01 -1.3070515e-01\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 9.1392122e-02 9.6495092e-02\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 -8.0248147e-02 1.6009660e-02\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -1.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1, "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, "system_info": {"OS": "Linux-5.4.0-137-generic-x86_64-with-glibc2.27 # 154-Ubuntu SMP Thu Jan 5 17:03:22 UTC 2023", "Python": "3.10.8", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.22.3", "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 0x7f5a28c4a5f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5a28c50580>"}, "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}}, "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. -10. -10.\n -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10.], (18,), 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, "num_timesteps": 20, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676810545216914887, "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": "[[ 1.4375114e+00 3.7055409e-01 -8.3448819e-04]\n [ 4.0368223e-01 1.1364377e+00 -8.3448819e-04]\n [-1.1124331e+00 -1.5997032e+00 -8.3448819e-04]\n [-7.2877222e-01 9.2787325e-02 -8.3448819e-04]]", "desired_goal": "[[ 1.6787918e+00 -1.7057517e+00 4.0767707e-05]\n [-2.5586367e-01 4.0557161e-01 4.0767707e-05]\n [-9.3583465e-01 4.5362788e-01 4.0767707e-05]\n [-4.8710012e-01 8.4655762e-01 4.0767707e-05]]", "observation": "[[-2.2828999e+00 1.8026731e+00 -6.9599640e-01 -2.5590426e-01\n -3.7827924e-01 -4.7194764e-01 1.4375114e+00 3.7055409e-01\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695971e-06\n 2.5336739e-02 -7.8686383e-03]\n [-1.8001274e+00 1.2900239e+00 1.7174590e+00 -6.2497097e-01\n 1.1568509e+00 1.4558060e-01 4.0368223e-01 1.1364377e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695967e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 6.1482060e-01 -1.0674846e-01 -2.2677412e+00 -1.1223067e+00\n 1.6859711e+00 -1.5176313e+00 -1.1124331e+00 -1.5997032e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0696285e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 8.1928092e-01 -2.6075025e+00 -1.4119338e+00 1.7270075e-01\n -7.5215530e-01 3.9653251e-01 -7.2877222e-01 9.2787325e-02\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695976e-06\n 2.5336739e-02 -7.8686383e-03]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.11815833 0.07831377 0.02 ]\n [ 0.02371145 0.13088465 0.02 ]\n [-0.11479533 -0.05692631 0.02 ]\n [-0.07974548 0.05924763 0.02 ]]", "desired_goal": "[[ 0.09253775 -0.09521101 0.02 ]\n [-0.04829011 0.05066176 0.02 ]\n [-0.0977867 0.053982 0.02 ]\n [-0.06512232 0.08112978 0.02 ]]", "observation": "[[ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 1.18158326e-01 7.83137679e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 2.37114523e-02 1.30884647e-01\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -1.14795335e-01 -5.69263138e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -7.97454789e-02 5.92476279e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -1.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1, "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, "system_info": {"OS": "Linux-5.4.0-137-generic-x86_64-with-glibc2.27 # 154-Ubuntu SMP Thu Jan 5 17:03:22 UTC 2023", "Python": "3.10.8", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
|
Binary file (465 kB). View file
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward": -
|
|
|
|
| 1 |
+
{"mean_reward": -8.305307834595443, "std_reward": 3.4123792706563814, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-19T12:42:28.742068"}
|