Upload model to Hugging Face

PPO-default.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716a8ee7ba08cd0c42f09034c669d0ccbfb51717a148ad71279d5c3e50fd8dbd
-size 136735
+oid sha256:3e9e1d9f1f6107d0473014c5a0bd1a528a7f8949342f98ae7a5576147400bc4a
+size 50432

PPO-default/data

@@ -4,20 +4,20 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc47ce053f0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc47ce05480>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc47ce05510>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc47ce055a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fc47ce05630>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fc47ce056c0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc47ce05750>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc47ce057e0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fc47ce05870>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc47ce05900>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc47ce05990>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc47ce05a20>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ff3c772d360>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3c772d3f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3c772d480>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3c772d510>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ff3c772d5a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ff3c772d630>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3c772d6c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3c772d750>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ff3c772d7e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3c772d870>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3c772d900>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3c772d990>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fc47ce01b00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ff3c77299c0>"
     },
     "verbose": true,
     "policy_kwargs": {},
@@ -43,40 +43,28 @@
         "_np_random": null
     },
     "n_envs": 4,
-    "num_timesteps": 106496,
-    "_total_timesteps": 100000,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1675310450205312370,
+    "start_time": null,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"
     },
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVpQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYwAAAAAAAAAAAAgD8AAIA/AACAPwAAgD/Sqnk/AACAP5g9Mj8AAIA/AACAP3Vacj4AAIA/+cB2P5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsDhpSMAUOUdJRSlC4="
-    },
-    "_last_episode_starts": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
-    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0649599999999999,
-    "ep_info_buffer": {
-        ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
-    },
-    "ep_success_buffer": {
-        ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
-    },
-    "_n_updates": 130,
+    "_current_progress_remaining": 1,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
     "n_steps": 2048,
     "gamma": 0.99,
     "gae_lambda": 0.95,

PPO-default/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf2de655a33791b8a75e93202104735f0b6a53a562c439408fb8b93aa1a05f0
-size 82809
+oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
+size 687

PPO-default/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89702bed8ac6691f6892eab18f6870397a39032c90142fc4b27d1d940237c93e
+oid sha256:13050dc1d60829d5814fb24155a293086d062e56c89e36fa83b7cdeff7b4618b
 size 40833

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Roomba
     metrics:
     - type: mean_reward
-      value: 97.60 +/- 128.05
+      value: -132.80 +/- 40.23
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc47ce053f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc47ce05480>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc47ce05510>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc47ce055a0>", "_build": "<function ActorCriticPolicy._build at 0x7fc47ce05630>", "forward": "<function ActorCriticPolicy.forward at 0x7fc47ce056c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc47ce05750>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc47ce057e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc47ce05870>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc47ce05900>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc47ce05990>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc47ce05a20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc47ce01b00>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[0. 0. 0.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 106496, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1675310450205312370, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVpQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYwAAAAAAAAAAAAgD8AAIA/AACAPwAAgD/Sqnk/AACAP5g9Mj8AAIA/AACAP3Vacj4AAIA/+cB2P5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsDhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0649599999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 130, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-58-generic-x86_64-with-glibc2.35 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.1", "Gym": "0.21.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7ff3c772d360>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3c772d3f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3c772d480>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3c772d510>", "_build": "<function ActorCriticPolicy._build at 0x7ff3c772d5a0>", "forward": "<function ActorCriticPolicy.forward at 0x7ff3c772d630>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3c772d6c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3c772d750>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff3c772d7e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3c772d870>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3c772d900>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3c772d990>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff3c77299c0>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[0. 0. 0.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-58-generic-x86_64-with-glibc2.35 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.1", "Gym": "0.21.0"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f67d514af5f54585b88ff554f05c4f96de36cfa68e25e07505c05de34e4534f
-size 1167964
+oid sha256:181f3254df6c4d71a5a1002ece2ba13b4ec5a7eaaab8573b613626c8bbb19c90
+size 1020071

results.json

@@ -1 +1 @@
-{"mean_reward": 97.6, "std_reward": 128.05327016519337, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-01T20:02:58.467391"}
+{"mean_reward": -132.8, "std_reward": 40.2313310741765, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-01T20:09:53.028748"}