Commit
•
70adc45
1
Parent(s):
f4094bf
Initial commit
Browse files- README.md +1 -1
- a2c-PandaReachDense-v3.zip +2 -2
- a2c-PandaReachDense-v3/actor.optimizer.pth +3 -0
- a2c-PandaReachDense-v3/critic.optimizer.pth +3 -0
- a2c-PandaReachDense-v3/data +50 -48
- a2c-PandaReachDense-v3/ent_coef_optimizer.pth +3 -0
- a2c-PandaReachDense-v3/policy.pth +2 -2
- a2c-PandaReachDense-v3/pytorch_variables.pth +2 -2
- config.json +1 -1
- results.json +1 -1
- vec_normalize.pkl +2 -2
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
type: PandaReachDense-v3
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value: -0.
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 16 |
type: PandaReachDense-v3
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: -0.28 +/- 0.06
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
a2c-PandaReachDense-v3.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:d19227c62f6c91d93eef13c901eedda625ec11e257572bed98d762f69959adb3
|
| 3 |
+
size 3142844
|
a2c-PandaReachDense-v3/actor.optimizer.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8b2bdbe7d71f8d5b05cb482c0c2dada49b87b6045784fc437cf348c9578a53
|
| 3 |
+
size 572238
|
a2c-PandaReachDense-v3/critic.optimizer.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b2ebf92efb0aa87281b24d40b72f497504cf24b8bec2571820d5038232b92ce
|
| 3 |
+
size 1132458
|
a2c-PandaReachDense-v3/data
CHANGED
|
@@ -1,86 +1,86 @@
|
|
| 1 |
{
|
| 2 |
"policy_class": {
|
| 3 |
":type:": "<class 'abc.ABCMeta'>",
|
| 4 |
-
":serialized:": "
|
| 5 |
-
"__module__": "stable_baselines3.
|
| 6 |
-
"__doc__": "\n
|
| 7 |
-
"__init__": "<function
|
| 8 |
"__abstractmethods__": "frozenset()",
|
| 9 |
-
"_abc_impl": "<_abc._abc_data object at
|
| 10 |
},
|
| 11 |
"verbose": 1,
|
| 12 |
"policy_kwargs": {
|
| 13 |
-
"
|
| 14 |
-
":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
|
| 15 |
-
"optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
|
| 16 |
-
"optimizer_kwargs": {
|
| 17 |
-
"alpha": 0.99,
|
| 18 |
-
"eps": 1e-05,
|
| 19 |
-
"weight_decay": 0
|
| 20 |
-
}
|
| 21 |
},
|
| 22 |
"num_timesteps": 1000000,
|
| 23 |
"_total_timesteps": 1000000,
|
| 24 |
"_num_timesteps_at_start": 0,
|
| 25 |
"seed": null,
|
| 26 |
"action_noise": null,
|
| 27 |
-
"start_time":
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
"tensorboard_log": null,
|
| 30 |
"_last_obs": {
|
| 31 |
":type:": "<class 'collections.OrderedDict'>",
|
| 32 |
-
":serialized:": "
|
| 33 |
-
"achieved_goal": "[[ 0.
|
| 34 |
-
"desired_goal": "[[ 1.
|
| 35 |
-
"observation": "[[
|
| 36 |
},
|
| 37 |
"_last_episode_starts": {
|
| 38 |
":type:": "<class 'numpy.ndarray'>",
|
| 39 |
-
":serialized:": "
|
| 40 |
},
|
| 41 |
"_last_original_obs": {
|
| 42 |
":type:": "<class 'collections.OrderedDict'>",
|
| 43 |
-
":serialized:": "
|
| 44 |
-
"achieved_goal": "[[
|
| 45 |
-
"desired_goal": "[[
|
| 46 |
-
"observation": "[[
|
| 47 |
},
|
| 48 |
-
"_episode_num":
|
| 49 |
"use_sde": false,
|
| 50 |
"sde_sample_freq": -1,
|
| 51 |
"_current_progress_remaining": 0.0,
|
| 52 |
"_stats_window_size": 100,
|
| 53 |
"ep_info_buffer": {
|
| 54 |
":type:": "<class 'collections.deque'>",
|
| 55 |
-
":serialized:": "
|
| 56 |
},
|
| 57 |
"ep_success_buffer": {
|
| 58 |
":type:": "<class 'collections.deque'>",
|
| 59 |
":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
|
| 60 |
},
|
| 61 |
-
"_n_updates":
|
| 62 |
-
"
|
|
|
|
|
|
|
|
|
|
| 63 |
"gamma": 0.99,
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"max_grad_norm": 0.5,
|
| 68 |
-
"rollout_buffer_class": {
|
| 69 |
":type:": "<class 'abc.ABCMeta'>",
|
| 70 |
-
":serialized:": "
|
| 71 |
"__module__": "stable_baselines3.common.buffers",
|
| 72 |
-
"__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}",
|
| 73 |
-
"__doc__": "\n Dict
|
| 74 |
-
"__init__": "<function
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"_get_samples": "<function DictRolloutBuffer._get_samples at 0x7dd2a33ca050>",
|
| 79 |
"__abstractmethods__": "frozenset()",
|
| 80 |
-
"_abc_impl": "<_abc._abc_data object at
|
| 81 |
},
|
| 82 |
-
"
|
| 83 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
"observation_space": {
|
| 85 |
":type:": "<class 'gymnasium.spaces.dict.Dict'>",
|
| 86 |
":serialized:": "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",
|
|
@@ -91,7 +91,7 @@
|
|
| 91 |
},
|
| 92 |
"action_space": {
|
| 93 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
| 94 |
-
":serialized:": "
|
| 95 |
"dtype": "float32",
|
| 96 |
"bounded_below": "[ True True True]",
|
| 97 |
"bounded_above": "[ True True True]",
|
|
@@ -102,11 +102,13 @@
|
|
| 102 |
"high": "[1. 1. 1.]",
|
| 103 |
"low_repr": "-1.0",
|
| 104 |
"high_repr": "1.0",
|
| 105 |
-
"_np_random":
|
| 106 |
},
|
| 107 |
"n_envs": 4,
|
| 108 |
"lr_schedule": {
|
| 109 |
":type:": "<class 'function'>",
|
| 110 |
-
":serialized:": "gAWVoAMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLA0sTQwx0AIgAfACDAYMBUwCUToWUjAVmbG9hdJSFlIwScHJvZ3Jlc3NfcmVtYWluaW5nlIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwIPGxhbWJkYT6US2FDAgwAlIwOdmFsdWVfc2NoZWR1bGWUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxJL3Vzci9sb2NhbC9saWIvcHl0aG9uMy4xMC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGghfZR9lChoGGgPjAxfX3F1YWxuYW1lX1+UjCFnZXRfc2NoZWR1bGVfZm4uPGxvY2Fscz4uPGxhbWJkYT6UjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgZjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOUaAIoaAcoSwFLAEsASwFLAUsTQwSIAFMAlGgJKYwBX5SFlGgOjARmdW5jlEuFQwIEAZSMA3ZhbJSFlCl0lFKUaBVOTmgdKVKUhZR0lFKUaCRoPn2UfZQoaBhoNWgnjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlGgpfZRoK05oLE5oLWgZaC5OaC9oMUc/
|
| 111 |
-
}
|
|
|
|
|
|
|
| 112 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"policy_class": {
|
| 3 |
":type:": "<class 'abc.ABCMeta'>",
|
| 4 |
+
":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
|
| 5 |
+
"__module__": "stable_baselines3.sac.policies",
|
| 6 |
+
"__doc__": "\n Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
| 7 |
+
"__init__": "<function MultiInputPolicy.__init__ at 0x7d2f068b5a20>",
|
| 8 |
"__abstractmethods__": "frozenset()",
|
| 9 |
+
"_abc_impl": "<_abc._abc_data object at 0x7d2f068be100>"
|
| 10 |
},
|
| 11 |
"verbose": 1,
|
| 12 |
"policy_kwargs": {
|
| 13 |
+
"use_sde": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
},
|
| 15 |
"num_timesteps": 1000000,
|
| 16 |
"_total_timesteps": 1000000,
|
| 17 |
"_num_timesteps_at_start": 0,
|
| 18 |
"seed": null,
|
| 19 |
"action_noise": null,
|
| 20 |
+
"start_time": 1717098617998433100,
|
| 21 |
+
"learning_rate": 0.0003,
|
| 22 |
"tensorboard_log": null,
|
| 23 |
"_last_obs": {
|
| 24 |
":type:": "<class 'collections.OrderedDict'>",
|
| 25 |
+
":serialized:": "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",
|
| 26 |
+
"achieved_goal": "[[ 0.8209939 0.46517685 0.24511373]\n [ 0.09861468 -0.47447753 -0.02250468]\n [-1.1282127 1.1856332 -0.8208811 ]\n [-0.838552 1.3393426 -0.9202334 ]]",
|
| 27 |
+
"desired_goal": "[[ 0.9907733 1.201106 -0.430969 ]\n [ 0.01619154 -0.9816673 -1.4385233 ]\n [-1.239361 0.7793549 -1.0192829 ]\n [-0.67555755 1.4491782 -1.4477941 ]]",
|
| 28 |
+
"observation": "[[ 0.8209939 0.46517685 0.24511373 0.08846838 2.0270162 -1.7783048 ]\n [ 0.09861468 -0.47447753 -0.02250468 -0.89712447 -2.1347668 -1.5273387 ]\n [-1.1282127 1.1856332 -0.8208811 -1.8169725 0.70786476 -0.6012894 ]\n [-0.838552 1.3393426 -0.9202334 -1.0634795 1.2298485 -1.0990644 ]]"
|
| 29 |
},
|
| 30 |
"_last_episode_starts": {
|
| 31 |
":type:": "<class 'numpy.ndarray'>",
|
| 32 |
+
":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
|
| 33 |
},
|
| 34 |
"_last_original_obs": {
|
| 35 |
":type:": "<class 'collections.OrderedDict'>",
|
| 36 |
+
":serialized:": "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",
|
| 37 |
+
"achieved_goal": "[[ 0.06553236 0.02468045 0.18224162]\n [ 0.02867897 -0.02455527 0.16669548]\n [-0.0339097 0.06243071 0.12031722]\n [-0.01913217 0.07048473 0.11454578]]",
|
| 38 |
+
"desired_goal": "[[ 0.08382189 0.10805087 0.10321331]\n [-0.0049421 -0.08887424 0.01170328]\n [-0.11929665 0.07000139 0.04978033]\n [-0.06794596 0.13043141 0.01086127]]",
|
| 39 |
+
"observation": "[[ 0.06553236 0.02468045 0.18224162 -0.15868676 1.1552145 -1.3428688 ]\n [ 0.02867897 -0.02455527 0.16669548 -0.5164538 -1.216599 -1.1860362 ]\n [-0.0339097 0.06243071 0.12031722 -0.8503557 0.4034259 -0.60733354]\n [-0.01913217 0.07048473 0.11454578 -0.57684016 0.7009061 -0.9184009 ]]"
|
| 40 |
},
|
| 41 |
+
"_episode_num": 302566,
|
| 42 |
"use_sde": false,
|
| 43 |
"sde_sample_freq": -1,
|
| 44 |
"_current_progress_remaining": 0.0,
|
| 45 |
"_stats_window_size": 100,
|
| 46 |
"ep_info_buffer": {
|
| 47 |
":type:": "<class 'collections.deque'>",
|
| 48 |
+
":serialized:": "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"
|
| 49 |
},
|
| 50 |
"ep_success_buffer": {
|
| 51 |
":type:": "<class 'collections.deque'>",
|
| 52 |
":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
|
| 53 |
},
|
| 54 |
+
"_n_updates": 249975,
|
| 55 |
+
"buffer_size": 1000000,
|
| 56 |
+
"batch_size": 256,
|
| 57 |
+
"learning_starts": 100,
|
| 58 |
+
"tau": 0.005,
|
| 59 |
"gamma": 0.99,
|
| 60 |
+
"gradient_steps": 1,
|
| 61 |
+
"optimize_memory_usage": false,
|
| 62 |
+
"replay_buffer_class": {
|
|
|
|
|
|
|
| 63 |
":type:": "<class 'abc.ABCMeta'>",
|
| 64 |
+
":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=",
|
| 65 |
"__module__": "stable_baselines3.common.buffers",
|
| 66 |
+
"__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}",
|
| 67 |
+
"__doc__": "\n Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n Extends the ReplayBuffer to use dictionary observations\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
| 68 |
+
"__init__": "<function DictReplayBuffer.__init__ at 0x7d2f069ed900>",
|
| 69 |
+
"add": "<function DictReplayBuffer.add at 0x7d2f069ed990>",
|
| 70 |
+
"sample": "<function DictReplayBuffer.sample at 0x7d2f069eda20>",
|
| 71 |
+
"_get_samples": "<function DictReplayBuffer._get_samples at 0x7d2f069edab0>",
|
|
|
|
| 72 |
"__abstractmethods__": "frozenset()",
|
| 73 |
+
"_abc_impl": "<_abc._abc_data object at 0x7d2f069e6300>"
|
| 74 |
},
|
| 75 |
+
"replay_buffer_kwargs": {},
|
| 76 |
+
"train_freq": {
|
| 77 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
| 78 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
| 79 |
+
},
|
| 80 |
+
"use_sde_at_warmup": false,
|
| 81 |
+
"target_entropy": -3.0,
|
| 82 |
+
"ent_coef": "auto",
|
| 83 |
+
"target_update_interval": 1,
|
| 84 |
"observation_space": {
|
| 85 |
":type:": "<class 'gymnasium.spaces.dict.Dict'>",
|
| 86 |
":serialized:": "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",
|
|
|
|
| 91 |
},
|
| 92 |
"action_space": {
|
| 93 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
| 94 |
+
":serialized:": "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",
|
| 95 |
"dtype": "float32",
|
| 96 |
"bounded_below": "[ True True True]",
|
| 97 |
"bounded_above": "[ True True True]",
|
|
|
|
| 102 |
"high": "[1. 1. 1.]",
|
| 103 |
"low_repr": "-1.0",
|
| 104 |
"high_repr": "1.0",
|
| 105 |
+
"_np_random": "Generator(PCG64)"
|
| 106 |
},
|
| 107 |
"n_envs": 4,
|
| 108 |
"lr_schedule": {
|
| 109 |
":type:": "<class 'function'>",
|
| 110 |
+
":serialized:": "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"
|
| 111 |
+
},
|
| 112 |
+
"batch_norm_stats": [],
|
| 113 |
+
"batch_norm_stats_target": []
|
| 114 |
}
|
a2c-PandaReachDense-v3/ent_coef_optimizer.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fd076ca1e8ff0632ff84417aab6fb7bc541c5d3c77f537b5f84d51f73ab220
|
| 3 |
+
size 1940
|
a2c-PandaReachDense-v3/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 sha256:9004fcb4ba2b5798a4dc04d5fadd2ecb0fd8fe434d0b03b235215d02d5ac411e
|
| 3 |
+
size 1417078
|
a2c-PandaReachDense-v3/pytorch_variables.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:a58089302787ca7ac2f61aa18b588e8b344fd0bf1630a475c4a70b3046265dde
|
| 3 |
+
size 1180
|
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 0x7dd2a3187400>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7dd2a3182940>"}, "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": 1717083770866958836, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.8585729 -1.1600014 -0.42559734]\n [ 0.1604491 0.00346191 0.41851398]\n [ 0.1604491 0.00346191 0.41851398]\n [-1.8705779 1.9303857 1.3741329 ]]", "desired_goal": "[[ 1.2531474 -1.285076 0.01739988]\n [ 1.2950222 0.06648976 1.1498717 ]\n [-0.14318718 -0.48747462 0.95674366]\n [-1.424789 1.3800982 1.0103146 ]]", "observation": "[[ 8.5857290e-01 -1.1600014e+00 -4.2559734e-01 3.7577891e-01\n -8.4176213e-01 -6.1572278e-01]\n [ 1.6044910e-01 3.4619095e-03 4.1851398e-01 4.4351456e-01\n -1.4601527e-03 3.6696327e-01]\n [ 1.6044910e-01 3.4619095e-03 4.1851398e-01 4.4351456e-01\n -1.4601527e-03 3.6696327e-01]\n [-1.8705779e+00 1.9303857e+00 1.3741329e+00 9.9304199e-02\n 6.5770948e-01 1.7237993e+00]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.09465133 0.05798246 0.06162997]\n [-0.08655246 0.03904167 0.08036593]\n [-0.08619738 0.03418663 0.02180653]\n [-0.03802622 -0.11435889 0.20461094]]", "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_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, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n Extends the RolloutBuffer to use dictionary observations\n\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to Monte-Carlo advantage estimate when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7dd2a33c9e10>", "reset": "<function DictRolloutBuffer.reset at 0x7dd2a33c9ea0>", "add": "<function DictRolloutBuffer.add at 0x7dd2a33c9f30>", "get": "<function DictRolloutBuffer.get at 0x7dd2a33c9fc0>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7dd2a33ca050>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7dd2a33cd240>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
|
|
|
|
| 1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.sac.policies", "__doc__": "\n Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ", "__init__": "<function MultiInputPolicy.__init__ at 0x7d2f068b5a20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d2f068be100>"}, "verbose": 1, "policy_kwargs": {"use_sde": false}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717098617998433100, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.8209939 0.46517685 0.24511373]\n [ 0.09861468 -0.47447753 -0.02250468]\n [-1.1282127 1.1856332 -0.8208811 ]\n [-0.838552 1.3393426 -0.9202334 ]]", "desired_goal": "[[ 0.9907733 1.201106 -0.430969 ]\n [ 0.01619154 -0.9816673 -1.4385233 ]\n [-1.239361 0.7793549 -1.0192829 ]\n [-0.67555755 1.4491782 -1.4477941 ]]", "observation": "[[ 0.8209939 0.46517685 0.24511373 0.08846838 2.0270162 -1.7783048 ]\n [ 0.09861468 -0.47447753 -0.02250468 -0.89712447 -2.1347668 -1.5273387 ]\n [-1.1282127 1.1856332 -0.8208811 -1.8169725 0.70786476 -0.6012894 ]\n [-0.838552 1.3393426 -0.9202334 -1.0634795 1.2298485 -1.0990644 ]]"}, "_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": "[[ 0.06553236 0.02468045 0.18224162]\n [ 0.02867897 -0.02455527 0.16669548]\n [-0.0339097 0.06243071 0.12031722]\n [-0.01913217 0.07048473 0.11454578]]", "desired_goal": "[[ 0.08382189 0.10805087 0.10321331]\n [-0.0049421 -0.08887424 0.01170328]\n [-0.11929665 0.07000139 0.04978033]\n [-0.06794596 0.13043141 0.01086127]]", "observation": "[[ 0.06553236 0.02468045 0.18224162 -0.15868676 1.1552145 -1.3428688 ]\n [ 0.02867897 -0.02455527 0.16669548 -0.5164538 -1.216599 -1.1860362 ]\n [-0.0339097 0.06243071 0.12031722 -0.8503557 0.4034259 -0.60733354]\n [-0.01913217 0.07048473 0.11454578 -0.57684016 0.7009061 -0.9184009 ]]"}, "_episode_num": 302566, "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 249975, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n Extends the ReplayBuffer to use dictionary observations\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ", "__init__": "<function DictReplayBuffer.__init__ at 0x7d2f069ed900>", "add": "<function DictReplayBuffer.add at 0x7d2f069ed990>", "sample": "<function DictReplayBuffer.sample at 0x7d2f069eda20>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7d2f069edab0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d2f069e6300>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -3.0, "ent_coef": "auto", "target_update_interval": 1, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward": -0.
|
|
|
|
| 1 |
+
{"mean_reward": -0.2781085465103388, "std_reward": 0.06392264650380905, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-30T21:20:26.781508"}
|
vec_normalize.pkl
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 sha256:2458dbc4286bc909a6e5ac78e567daaaf37709b4ecb39b71d390ae71c36be8a6
|
| 3 |
+
size 2848
|