Test render

PPO-asm-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e3040c6c86be1f2cf349dc522b6cb74c2a16985c0f332b3744fd4fee58b62b
+oid sha256:f8a1b9da40221a0abf384b4ccb03f47e62c3b4010ad4bf7a380373c93501b289
 size 129920

PPO-asm-v0/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 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>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f9c57b23880>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9c57b23920>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9c57b239c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9c57b23a60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9c57b23b00>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9c57b23ba0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9c57b23c40>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9c57b23ce0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9c57b23d80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9c57b23e20>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9c57b23ec0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9c57b23f60>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f0c0aeb2b80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f9c57b38700>"
     },
     "verbose": 0,
     "policy_kwargs": {},
@@ -26,7 +26,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1704321519261305921,
+    "start_time": 1704322583040231963,
     "learning_rate": 0.0003,
     "tensorboard_log": "/home/jovyan/logs",
     "_last_obs": {
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV4gAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQAUEAo5PuXyMAWyUTegDjAF0lEdACfJlrdnCf3V9lChoBkc/5FMyrPt2LmgHTegDaAhHQA9qvmozeoF1fZQoaAZHP/yAxBVuJk5oB03oA2gIR0AWO2AoXsPbdX2UKGgGRz/01QAMlTm5aAdN6ANoCEdAGQkmx+rlvXV9lChoBkc/1tMj/uLJjmgHTegDaAhHQB+ihzvJA+p1fZQoaAZHP/qwQUYbbURoB03oA2gIR0AhLkBCD28JdWUu"
+        ":serialized:": "gAWV4gAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHP+Q7YChew9uMAWyUTegDjAF0lEdAAXc6/7BO6HV9lChoBkc/9v+zdDYywmgHTegDaAhHQAcYY77sOXp1fZQoaAZHQBNZlOGj9GZoB03oA2gIR0ASCpDNQj2SdX2UKGgGR0AUrFo+OfdzaAdN6ANoCEdAFL5paiblR3V9lChoBkc//YYqG1x82WgHTegDaAhHQBtLBj4Hoox1fZQoaAZHQAAh7u2JBPdoB03oA2gIR0AeCUgSvkimdWUu"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

PPO-asm-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9678462483f1414435c60dd797857cab87ca2361a9ca6357bba5b8234874720a
+oid sha256:1a57aad0119b603581732bd67cc48664dd696aca0f5f0a4eb6463f63530efff7
 size 79920

PPO-asm-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2199ffa5de0402a7379a4fe9495e997733d977f7dda9d234764a0783cb77d11
+oid sha256:09a983bc829155dd7839b26a12ced4c6cbdde771438dc02d0f16a021faf738d8
 size 39294

README.md

@@ -16,7 +16,7 @@ model-index:
       type: asm-v0
     metrics:
     - type: mean_reward
-      value: 2.23 +/- 1.05
+      value: 2.08 +/- 1.16
       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 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"}}
+{"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 0x7f9c57b23880>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9c57b23920>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9c57b239c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9c57b23a60>", "_build": "<function ActorCriticPolicy._build at 0x7f9c57b23b00>", "forward": "<function ActorCriticPolicy.forward at 0x7f9c57b23ba0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9c57b23c40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9c57b23ce0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9c57b23d80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9c57b23e20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9c57b23ec0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9c57b23f60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9c57b38700>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 6144, "_total_timesteps": 6000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704322583040231963, "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:": "gAWV4gAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHP+Q7YChew9uMAWyUTegDjAF0lEdAAXc6/7BO6HV9lChoBkc/9v+zdDYywmgHTegDaAhHQAcYY77sOXp1fZQoaAZHQBNZlOGj9GZoB03oA2gIR0ASCpDNQj2SdX2UKGgGR0AUrFo+OfdzaAdN6ANoCEdAFL5paiblR3V9lChoBkc//YYqG1x82WgHTegDaAhHQBtLBj4Hoox1fZQoaAZHQAAh7u2JBPdoB03oA2gIR0AeCUgSvkimdWUu"}, "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:": "gAWViQEAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAABlGgIjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKUjA1ib3VuZGVkX2Fib3ZllGgRKJYBAAAAAAAAAAGUaBVLAYWUaBl0lFKUjAZfc2hhcGWUSwGFlIwDbG93lGgRKJYEAAAAAAAAAAAAgL+UaAtLAYWUaBl0lFKUjARoaWdolGgRKJYEAAAAAAAAAAAAgD+UaAtLAYWUaBl0lFKUjAhsb3dfcmVwcpSMBC0xLjCUjAloaWdoX3JlcHKUjAMxLjCUjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV5gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjFIvc3J2L2NvbmRhL2VudnMvc2IzL2xpYi9weXRob24zLjExL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4NDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMUi9zcnYvY29uZGEvZW52cy9zYjMvbGliL3B5dGhvbjMuMTEvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIX2UfZQoaBhoDYwMX19xdWFsbmFtZV9flGgOjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgZjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": 2.2269047, "std_reward": 1.054063073665713, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-03T22:38:52.813390"}
+{"mean_reward": 2.0840184, "std_reward": 1.1585796033335993, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-03T22:56:34.878078"}