optimized hyperparameters (optuna) trained locally on A4000, adam
Browse files- README.md +1 -1
- a2c-PandaReachDense-v2.zip +2 -2
- a2c-PandaReachDense-v2/data +11 -11
- a2c-PandaReachDense-v2/policy.optimizer.pth +1 -1
- a2c-PandaReachDense-v2/policy.pth +1 -1
- 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: -0.
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 16 |
type: PandaReachDense-v2
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: -0.39 +/- 0.15
|
| 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 sha256:99534d3b05a9e724ed7867c4473b0281be6c60423dc2312f98f36a68c0d52012
|
| 3 |
+
size 148490
|
a2c-PandaReachDense-v2/data
CHANGED
|
@@ -10,12 +10,12 @@
|
|
| 10 |
},
|
| 11 |
"verbose": 1,
|
| 12 |
"policy_kwargs": {},
|
| 13 |
-
"num_timesteps":
|
| 14 |
-
"_total_timesteps":
|
| 15 |
-
"_num_timesteps_at_start":
|
| 16 |
"seed": null,
|
| 17 |
"action_noise": null,
|
| 18 |
-
"start_time":
|
| 19 |
"learning_rate": 0.000578402569656186,
|
| 20 |
"tensorboard_log": null,
|
| 21 |
"lr_schedule": {
|
|
@@ -24,10 +24,10 @@
|
|
| 24 |
},
|
| 25 |
"_last_obs": {
|
| 26 |
":type:": "<class 'collections.OrderedDict'>",
|
| 27 |
-
":serialized:": "
|
| 28 |
-
"achieved_goal": "[[0.
|
| 29 |
-
"desired_goal": "[[0.
|
| 30 |
-
"observation": "[[ 3.
|
| 31 |
},
|
| 32 |
"_last_episode_starts": {
|
| 33 |
":type:": "<class 'numpy.ndarray'>",
|
|
@@ -35,9 +35,9 @@
|
|
| 35 |
},
|
| 36 |
"_last_original_obs": {
|
| 37 |
":type:": "<class 'collections.OrderedDict'>",
|
| 38 |
-
":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
| 39 |
"achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
|
| 40 |
-
"desired_goal": "[[0.
|
| 41 |
"observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
|
| 42 |
},
|
| 43 |
"_episode_num": 0,
|
|
@@ -52,7 +52,7 @@
|
|
| 52 |
":type:": "<class 'collections.deque'>",
|
| 53 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 54 |
},
|
| 55 |
-
"_n_updates":
|
| 56 |
"n_steps": 8,
|
| 57 |
"gamma": 0.9165585983844102,
|
| 58 |
"gae_lambda": 1.0,
|
|
|
|
| 10 |
},
|
| 11 |
"verbose": 1,
|
| 12 |
"policy_kwargs": {},
|
| 13 |
+
"num_timesteps": 212000,
|
| 14 |
+
"_total_timesteps": 212000,
|
| 15 |
+
"_num_timesteps_at_start": 200000,
|
| 16 |
"seed": null,
|
| 17 |
"action_noise": null,
|
| 18 |
+
"start_time": 1683470165682997304,
|
| 19 |
"learning_rate": 0.000578402569656186,
|
| 20 |
"tensorboard_log": null,
|
| 21 |
"lr_schedule": {
|
|
|
|
| 24 |
},
|
| 25 |
"_last_obs": {
|
| 26 |
":type:": "<class 'collections.OrderedDict'>",
|
| 27 |
+
":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA0rbMPiHwZjt72RE/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAjyoAP7wqtr/nkmm/lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADStsw+IfBmO3vZET+TdKC8NwcUuqceRDuUaA5LAUsGhpRoEnSUUpR1Lg==",
|
| 28 |
+
"achieved_goal": "[[0.3998323 0.00352383 0.56972474]]",
|
| 29 |
+
"desired_goal": "[[ 0.5006494 -1.4231791 -0.9123978]]",
|
| 30 |
+
"observation": "[[ 3.9983231e-01 3.5238343e-03 5.6972474e-01 -1.9586837e-02\n -5.6468270e-04 2.9925497e-03]]"
|
| 31 |
},
|
| 32 |
"_last_episode_starts": {
|
| 33 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
|
| 35 |
},
|
| 36 |
"_last_original_obs": {
|
| 37 |
":type:": "<class 'collections.OrderedDict'>",
|
| 38 |
+
":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAWJHvvYzz+rxQbJQ9lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==",
|
| 39 |
"achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
|
| 40 |
+
"desired_goal": "[[-0.11697644 -0.03063371 0.07247221]]",
|
| 41 |
"observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
|
| 42 |
},
|
| 43 |
"_episode_num": 0,
|
|
|
|
| 52 |
":type:": "<class 'collections.deque'>",
|
| 53 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 54 |
},
|
| 55 |
+
"_n_updates": 26500,
|
| 56 |
"n_steps": 8,
|
| 57 |
"gamma": 0.9165585983844102,
|
| 58 |
"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 92400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:280770c87350dae7dd0aefc3876c64582929dbcf383d934f191f5ebd1604d5d0
|
| 3 |
size 92400
|
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 sha256:878cbcfd220855c6866e0815345087ef6385290d4273cf1816f9ce92f89f0825
|
| 3 |
size 46014
|
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 0x7f9e13f6d3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9e13f6c580>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps":
|
|
|
|
| 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 0x7f9e13f6d3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9e13f6c580>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 212000, "_total_timesteps": 212000, "_num_timesteps_at_start": 200000, "seed": null, "action_noise": null, "start_time": 1683470165682997304, "learning_rate": 0.000578402569656186, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVzwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjE8vaG9tZS9taWtpLy5sb2NhbC9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgkMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxPL2hvbWUvbWlraS8ubG9jYWwvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoF2gOjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGIwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/QvP+D2+t5YWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA0rbMPiHwZjt72RE/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAjyoAP7wqtr/nkmm/lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADStsw+IfBmO3vZET+TdKC8NwcUuqceRDuUaA5LAUsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[0.3998323 0.00352383 0.56972474]]", "desired_goal": "[[ 0.5006494 -1.4231791 -0.9123978]]", "observation": "[[ 3.9983231e-01 3.5238343e-03 5.6972474e-01 -1.9586837e-02\n -5.6468270e-04 2.9925497e-03]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAWJHvvYzz+rxQbJQ9lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", "desired_goal": "[[-0.11697644 -0.03063371 0.07247221]]", "observation": "[[ 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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 26500, "n_steps": 8, "gamma": 0.9165585983844102, "gae_lambda": 1.0, "ent_coef": 0.00034210500957356594, "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": 1, "system_info": {"OS": "Linux-5.14.0-239.el9.x86_64-x86_64-with-glibc2.34 # 1 SMP PREEMPT_DYNAMIC Thu Jan 19 14:14:19 UTC 2023", "Python": "3.9.16", "Stable-Baselines3": "1.8.0a13", "PyTorch": "2.0.0+cu117", "GPU Enabled": "True", "Numpy": "1.21.2", "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": -0.
|
|
|
|
| 1 |
+
{"mean_reward": -0.3890290173701942, "std_reward": 0.1464069341748745, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-07T16:43:35.605599"}
|
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 sha256:52f0dae9a753ff553cc02e945283a4954c60478f84129e249c3b6b7b98044114
|
| 3 |
size 2381
|