Test commit

PPO-asm-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e3040c6c86be1f2cf349dc522b6cb74c2a16985c0f332b3744fd4fee58b62b
+size 129920

PPO-asm-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

PPO-asm-v0/data

@@ -0,0 +1,105 @@
+{
+    "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 0x7f0c0aeb7920>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0c0aeb79c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0c0aeb7a60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0c0aeb7b00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0c0aeb7ba0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0c0aeb7c40>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0c0aeb7ce0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0c0aeb7d80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0c0aeb7e20>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0c0aeb7ec0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0c0aeb7f60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0c0aecc040>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f0c0aeb2b80>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {},
+    "num_timesteps": 6144,
+    "_total_timesteps": 6000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1704321519261305921,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "/home/jovyan/logs",
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAgL+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLAYaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.02400000000000002,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWV4gAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQAUEAo5PuXyMAWyUTegDjAF0lEdACfJlrdnCf3V9lChoBkc/5FMyrPt2LmgHTegDaAhHQA9qvmozeoF1fZQoaAZHP/yAxBVuJk5oB03oA2gIR0AWO2AoXsPbdX2UKGgGRz/01QAMlTm5aAdN6ANoCEdAGQkmx+rlvXV9lChoBkc/1tMj/uLJjmgHTegDaAhHQB+ihzvJA+p1fZQoaAZHP/qwQUYbbURoB03oA2gIR0AhLkBCD28JdWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 30,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_shape": [
+            1
+        ],
+        "low": "[-1.]",
+        "high": "[1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_shape": [
+            1
+        ],
+        "low": "[-1.]",
+        "high": "[1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "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,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

PPO-asm-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9678462483f1414435c60dd797857cab87ca2361a9ca6357bba5b8234874720a
+size 79920

PPO-asm-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2199ffa5de0402a7379a4fe9495e997733d977f7dda9d234764a0783cb77d11
+size 39294

PPO-asm-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

PPO-asm-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.5.6-76060506-generic-x86_64-with-glibc2.35 # 202310061235~1697396945~22.04~9283e32 SMP PREEMPT_DYNAMIC Sun O
+- Python: 3.11.5
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: True
+- Numpy: 1.26.3
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: stable-baselines3
 tags:
-- MountainCarContinuous-v0
+- asm-v0
 - deep-reinforcement-learning
 - reinforcement-learning
 - stable-baselines3
@@ -12,17 +12,17 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: MountainCarContinuous-v0
-      type: MountainCarContinuous-v0
+      name: asm-v0
+      type: asm-v0
     metrics:
     - type: mean_reward
-      value: -0.00 +/- 0.00
+      value: 2.23 +/- 1.05
       name: mean_reward
       verified: false
 ---
 
-# **PPO** Agent playing **MountainCarContinuous-v0**
-This is a trained model of a **PPO** agent playing **MountainCarContinuous-v0**
+# **PPO** Agent playing **asm-v0**
+This is a trained model of a **PPO** agent playing **asm-v0**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)

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 0x7f8a7c721e40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8a7c721ee0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8a7c721f80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8a7c722020>", "_build": "<function ActorCriticPolicy._build at 0x7f8a7c7220c0>", "forward": "<function ActorCriticPolicy.forward at 0x7f8a7c722160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8a7c722200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8a7c7222a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8a7c722340>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8a7c7223e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8a7c722480>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8a7c722520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8a7c71aec0>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 61440, "_total_timesteps": 60000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704319474446146305, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAIsC3b636dc7lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_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": 330, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "low_repr": "[-1.2  -0.07]", "high_repr": "[0.6  0.07]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-1.]", "high": "[1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 1, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.5.6-76060506-generic-x86_64-with-glibc2.35 # 202310061235~1697396945~22.04~9283e32 SMP PREEMPT_DYNAMIC Sun O", "Python": "3.11.5", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}
+{"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 0x7f0c0aeb7920>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0c0aeb79c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0c0aeb7a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0c0aeb7b00>", "_build": "<function ActorCriticPolicy._build at 0x7f0c0aeb7ba0>", "forward": "<function ActorCriticPolicy.forward at 0x7f0c0aeb7c40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0c0aeb7ce0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0c0aeb7d80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0c0aeb7e20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0c0aeb7ec0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0c0aeb7f60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0c0aecc040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0c0aeb2b80>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 6144, "_total_timesteps": 6000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704321519261305921, "learning_rate": 0.0003, "tensorboard_log": "/home/jovyan/logs", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAgL+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLAYaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4gAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQAUEAo5PuXyMAWyUTegDjAF0lEdACfJlrdnCf3V9lChoBkc/5FMyrPt2LmgHTegDaAhHQA9qvmozeoF1fZQoaAZHP/yAxBVuJk5oB03oA2gIR0AWO2AoXsPbdX2UKGgGRz/01QAMlTm5aAdN6ANoCEdAGQkmx+rlvXV9lChoBkc/1tMj/uLJjmgHTegDaAhHQB+ihzvJA+p1fZQoaAZHP/qwQUYbbURoB03oA2gIR0AhLkBCD28JdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 30, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-1.]", "high": "[1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-1.]", "high": "[1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 1, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.5.6-76060506-generic-x86_64-with-glibc2.35 # 202310061235~1697396945~22.04~9283e32 SMP PREEMPT_DYNAMIC Sun O", "Python": "3.11.5", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.26.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -0.0009039, "std_reward": 0.0004166944804050084, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-03T22:06:06.728337"}
+{"mean_reward": 2.2269047, "std_reward": 1.054063073665713, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-03T22:38:52.813390"}