Push to Hub

DQN-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f293c65086dd82adf46cdb91ccbf18b18a23f5ff5d2eb0569dcd7f809eb9fe
+size 1108550

DQN-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.2

DQN-CartPole-v1/data

@@ -0,0 +1,131 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.dqn.policies",
+        "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}",
+        "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\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 features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\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 DQNPolicy.__init__ at 0x7168594dec10>",
+        "_build": "<function DQNPolicy._build at 0x7168594deca0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7168594ded30>",
+        "forward": "<function DQNPolicy.forward at 0x7168594dedc0>",
+        "_predict": "<function DQNPolicy._predict at 0x7168594dee50>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7168594deee0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7168594def70>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7168594dfdc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000.0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1721811460312841925,
+    "learning_rate": 0.0001,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAKgCED/NdKE+YfNaPAxqGT6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAEdlDT/6vAI/9LeFPCmFF76UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 2056,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 24975,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_shape": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1000000,
+    "batch_size": 32,
+    "learning_starts": 100,
+    "tau": 1.0,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\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        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\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 ReplayBuffer.__init__ at 0x7168595fe280>",
+        "add": "<function ReplayBuffer.add at 0x7168595fe310>",
+        "sample": "<function ReplayBuffer.sample at 0x7168595fe3a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7168595fe430>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7168595e9e50>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7168595f9fc0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.05,
+    "exploration_fraction": 0.1,
+    "target_update_interval": 10000,
+    "_n_calls": 100000,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.05,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

DQN-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c5d4a675c4dcb47acc6f294aba3a736e53ca36cc1c8edde48d2030d871c7da
+size 545952

DQN-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610d2607e8298a347698350ce83c5f0867284ad86ba099f560ba50c6508253f2
+size 545074

DQN-CartPole-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

DQN-CartPole-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.5.0-41-generic-x86_64-with-glibc2.35 # 41~22.04.2-Ubuntu SMP PREEMPT_DYNAMIC Mon Jun  3 11:32:55 UTC 2
+- Python: 3.9.19
+- Stable-Baselines3: 2.3.2
+- PyTorch: 2.4.0+cpu
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 249.70 +/- 15.98
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **CartPole-v1**
+This is a trained model of a **DQN** agent playing **CartPole-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=", "__module__": "stable_baselines3.dqn.policies", "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}", "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\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 features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\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 DQNPolicy.__init__ at 0x7168594dec10>", "_build": "<function DQNPolicy._build at 0x7168594deca0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7168594ded30>", "forward": "<function DQNPolicy.forward at 0x7168594dedc0>", "_predict": "<function DQNPolicy._predict at 0x7168594dee50>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7168594deee0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7168594def70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7168594dfdc0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": [256, 256]}, "num_timesteps": 100000, "_total_timesteps": 100000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1721811460312841925, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAKgCED/NdKE+YfNaPAxqGT6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAEdlDT/6vAI/9LeFPCmFF76UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 2056, "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 24975, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVFgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAABAQEBlGgIjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKUjA1ib3VuZGVkX2Fib3ZllGgRKJYEAAAAAAAAAAEBAQGUaBVLBIWUaBl0lFKUjAZfc2hhcGWUSwSFlIwDbG93lGgRKJYQAAAAAAAAAJqZmcD//3//UHfWvv//f/+UaAtLBIWUaBl0lFKUjARoaWdolGgRKJYQAAAAAAAAAJqZmUD//39/UHfWPv//f3+UaAtLBIWUaBl0lFKUjAhsb3dfcmVwcpSMPVstNC44MDAwMDAyZSswMCAtMy40MDI4MjM1ZSszOCAtNC4xODg3OTAzZS0wMSAtMy40MDI4MjM1ZSszOF2UjAloaWdoX3JlcHKUjDlbNC44MDAwMDAyZSswMCAzLjQwMjgyMzVlKzM4IDQuMTg4NzkwM2UtMDEgMy40MDI4MjM1ZSszOF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 32, "learning_starts": 100, "tau": 1.0, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}", "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\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        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\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 ReplayBuffer.__init__ at 0x7168595fe280>", "add": "<function ReplayBuffer.add at 0x7168595fe310>", "sample": "<function ReplayBuffer.sample at 0x7168595fe3a0>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7168595fe430>", "_maybe_cast_dtype": "<staticmethod object at 0x7168595e9e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7168595f9fc0>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.05, "exploration_fraction": 0.1, "target_update_interval": 10000, "_n_calls": 100000, "max_grad_norm": 10, "exploration_rate": 0.05, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.5.0-41-generic-x86_64-with-glibc2.35 # 41~22.04.2-Ubuntu SMP PREEMPT_DYNAMIC Mon Jun  3 11:32:55 UTC 2", "Python": "3.9.19", "Stable-Baselines3": "2.3.2", "PyTorch": "2.4.0+cpu", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 249.7, "std_reward": 15.975293424535275, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-24T14:29:38.687755"}