Done

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 268.51 +/- 18.51
+      value: -329.46 +/- 193.97
       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 0x79318d9596c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79318d959750>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79318d9597e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79318d959870>", "_build": "<function ActorCriticPolicy._build at 0x79318d959900>", "forward": "<function ActorCriticPolicy.forward at 0x79318d959990>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79318d959a20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79318d959ab0>", "_predict": "<function ActorCriticPolicy._predict at 0x79318d959b40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79318d959bd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79318d959c60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79318d959cf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79318d955e40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 45104, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689947856582099948, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.967232, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 256, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7b1d080064d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b1d08006560>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b1d080065f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b1d08006680>", "_build": "<function ActorCriticPolicy._build at 0x7b1d08006710>", "forward": "<function ActorCriticPolicy.forward at 0x7b1d080067a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b1d08006830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b1d080068c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7b1d08006950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b1d080069e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b1d08006a70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b1d08006b00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b1d0800cf00>"}, "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": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690139162328979320, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1250, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo_model_marina.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb9cb1f0e656e00ad4e08f857b60b1e0619960e152ff8ee7b7aefac21ac4d6f
-size 144998
+oid sha256:72d39c946ebb4e3896e11bff9ccf8af080970bab346e9764684d8ea34ebf94f8
+size 96648

ppo_model_marina/data

@@ -4,34 +4,43 @@
         ":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 0x79318d9596c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79318d959750>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79318d9597e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79318d959870>",
-        "_build": "<function ActorCriticPolicy._build at 0x79318d959900>",
-        "forward": "<function ActorCriticPolicy.forward at 0x79318d959990>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x79318d959a20>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79318d959ab0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x79318d959b40>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79318d959bd0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79318d959c60>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x79318d959cf0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7b1d080064d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b1d08006560>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b1d080065f0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b1d08006680>",
+        "_build": "<function ActorCriticPolicy._build at 0x7b1d08006710>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7b1d080067a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b1d08006830>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b1d080068c0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7b1d08006950>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b1d080069e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b1d08006a70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b1d08006b00>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x79318d955e40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7b1d0800cf00>"
     },
     "verbose": 1,
-    "policy_kwargs": {},
-    "num_timesteps": 45104,
-    "_total_timesteps": 1000000,
+    "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": 100000,
+    "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1689947856582099948,
-    "learning_rate": 0.0003,
+    "start_time": 1690139162328979320,
+    "learning_rate": 0.0007,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,20 +50,20 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 0.967232,
+    "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 256,
+    "_n_updates": 1250,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "bounded_below": "[ True  True  True  True  True  True  True  True]",
         "bounded_above": "[ True  True  True  True  True  True  True  True]",
@@ -69,7 +78,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -77,23 +86,15 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "n_steps": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
+    "n_steps": 5,
+    "gamma": 0.99,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 4,
-    "clip_range": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
-    },
-    "clip_range_vf": null,
-    "normalize_advantage": true,
-    "target_kl": null,
+    "normalize_advantage": false,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     }
 }

ppo_model_marina/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3237f4b85e326cd0400d873d80deda9704c4c4f867e3a3493d17c9c6bc0b943c
-size 87929
+oid sha256:22ab5a2dfd6cf713d032ebc249b807131b55d7afa7920a7a3acae055da090356
+size 42625

ppo_model_marina/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145042fac38d662a08018e3a55e25ce2f87113e796ff1da7823754ef0218eae8
+oid sha256:5bbaa470f3087c1b53061d5bc4ff7ab07b05c20edaec21c7f5ea980aa4bc94bf
 size 43329

results.json

@@ -1 +1 @@
-{"mean_reward": 268.5120841, "std_reward": 18.512824670890353, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-21T13:59:24.687871"}
+{"mean_reward": -329.4648154, "std_reward": 193.96651404363888, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-23T19:12:41.946797"}