The PPO agent trained for the environment LunarLander-v2 as part of Introduction to Reinforcement Unit 1

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 240.83 +/- 64.63
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+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:": "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 0x7c410f498f40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c410f498fe0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c410f499080>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c410f499120>", "_build": "<function ActorCriticPolicy._build at 0x7c410f4991c0>", "forward": "<function ActorCriticPolicy.forward at 0x7c410f499260>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c410f499300>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c410f4993a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c410f499440>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c410f4994e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c410f499580>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c410f499620>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c410f3bcec0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1737267943757515322, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAuQr222ls91WbiPD61c76g2GM8EzkRvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -0.00044800000000000395, "_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": 3908, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2-Shahzeb.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1730372eba80a05f5959c0b3b05cc40108d603bde33c6b7a0a18391717166f51
+size 147462

ppo-LunarLander-v2-Shahzeb/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2-Shahzeb/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7c410f498f40>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c410f498fe0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c410f499080>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c410f499120>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c410f4991c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c410f499260>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c410f499300>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c410f4993a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c410f499440>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c410f4994e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c410f499580>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c410f499620>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7c410f3bcec0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1737267943757515322,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAuQr222ls91WbiPD61c76g2GM8EzkRvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_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": -0.00044800000000000395,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVOgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG39zi0fHPyMAWyUTUwBjAF0lEdAnZ4EOqebu3V9lChoBkdAcM+TfBN21WgHTZkBaAhHQJ2hYwBYFJR1fZQoaAZHQG/N1wo9cKRoB01mAWgIR0Cdo0yQxN7CdX2UKGgGR0BxVNe6Zpi7aAdNmgFoCEdAnaV3bZezEHV9lChoBkdAbgHHCGetjmgHTS8BaAhHQJ2oM/s3Q2N1fZQoaAZHQHCJzy8SPENoB01aAWgIR0CdqiX9itq6dX2UKGgGR0BtWBlnRLK3aAdNWQFoCEdAnayWVZ9uxnV9lChoBkdAbbK06YE4emgHTUsBaAhHQJ2wY4zabnZ1fZQoaAZHQHKOjz3AVO9oB00+AWgIR0Cdstc5sCT2dX2UKGgGR0Bwt3iIcinpaAdNOwFoCEdAnbT31jAi3XV9lChoBkdAauqYb83uNWgHTVkBaAhHQJ24EIVuaWp1fZQoaAZHQG7+r2YfGMpoB00uAWgIR0CdubGACnxbdX2UKGgGR0BwP8i6g/TtaAdNKAFoCEdAnbtRQm/nGXV9lChoBkdAcSoNyHVPN2gHTWsBaAhHQJ2+Zn7Hhjx1fZQoaAZHQC7CXv6TGHZoB0v6aAhHQJ2/vLfUF0R1fZQoaAZHQHDNSWRigChoB01eAWgIR0CdwZpsXSBtdX2UKGgGR0BtSPj4pMHsaAdNSgFoCEdAncSjnNgSe3V9lChoBkdAb9E2qkuYhWgHTToBaAhHQJ3GYbFS88N1fZQoaAZHQEAiNp/PPcBoB0vxaAhHQJ3HrfJmukl1fZQoaAZHQHC8MrRSgoRoB00pAWgIR0CdyUR8twrEdX2UKGgGR0BwUdOpKjBVaAdNbwFoCEdAncx0eIVM23V9lChoBkdAcCE/aQFLWmgHTU0BaAhHQJ3OPJEH+qB1fZQoaAZHQDXt32VVxS5oB0vpaAhHQJ3PjuWrwOR1fZQoaAZHQHJKIllbu+hoB00rAWgIR0Cd0kZLqUu+dX2UKGgGR0Byx9/y5I6KaAdNPgFoCEdAndQTd1uBMHV9lChoBkdAbgR2r4nF52gHTUcBaAhHQJ3Vy3vx6OZ1fZQoaAZHQGJZZftx+8ZoB03oA2gIR0Cd3KMhX8wYdX2UKGgGR0Bw5A8kleF+aAdNNAFoCEdAnd7EcbR4QnV9lChoBkdAb8DiH6/IsGgHTUIBaAhHQJ3iiiO/+Kl1fZQoaAZHQHDAhRuTA31oB008AWgIR0Cd5Pu7HyVfdX2UKGgGR0BN1yXt0FKTaAdL+mgIR0Cd5tND+irUdX2UKGgGR0BLDJVjqfOEaAdLu2gIR0Cd6ZXEIgNgdX2UKGgGR0BsTF+gDifhaAdNXgFoCEdAneuEbYK6WnV9lChoBkdAcPWgc94eLmgHTWgBaAhHQJ3tehIvrW11fZQoaAZHQHKCqVQhwERoB01YAWgIR0Cd8H5PM0P6dX2UKGgGR0BuiPiaRZEEaAdNJwFoCEdAnfIPPPcBVHV9lChoBkdAcNuBl+Vkc2gHTT0BaAhHQJ3zy9K28Zl1fZQoaAZHQGBM349HMEBoB03oA2gIR0Cd+lntOVPfdX2UKGgGR0Bsc1Au7HyVaAdNSgFoCEdAnfwqF7D2rXV9lChoBkdAcKq+zdDYy2gHTVcBaAhHQJ3/IidJ8OV1fZQoaAZHQHDu3E/B3zNoB017AWgIR0CeATuV5a/zdX2UKGgGR0BujcEPlMh6aAdNKgFoCEdAngLVCCz1LHV9lChoBkdAcANwKjSG8GgHTWcBaAhHQJ4F8siB5HF1fZQoaAZHQG5l2/zreIloB01GAWgIR0CeB8CQtBfKdX2UKGgGR0BuG1BlcyFgaAdNQwFoCEdAngmKkqMFU3V9lChoBkdAbxne7cwg1WgHTXcBaAhHQJ4M5qJuVHF1fZQoaAZHQHHE1ENOM2poB01rAWgIR0CeDtV+7UXpdX2UKGgGR0BwMoZrHlwMaAdNhAFoCEdAnhKYZl4C63V9lChoBkdAb4NC4SYgJWgHTcQBaAhHQJ4VqL5ylvZ1fZQoaAZHQG5K9Nvfj0doB03RAWgIR0CeGTYQJ5VwdX2UKGgGR0BsO6bSZ0CBaAdNjwFoCEdAnh1uDFqBVnV9lChoBkdARKfT5O8CgmgHS+NoCEdAnh6iobXHznV9lChoBkdAcCZDOTq0MWgHTV8BaAhHQJ4gf4k/r0J1fZQoaAZHQG5dy2hIvrZoB03LA2gIR0CeJvjZcs19dX2UKGgGR0BvoZ+x4Y78aAdNTAFoCEdAnioCSq2jPHV9lChoBkdAXkSQJXyRS2gHTegDaAhHQJ4wmdJ8OTd1fZQoaAZHQHCCoM4LkS5oB03KAWgIR0CeMxJbMX7+dX2UKGgGR0Bv/cSZjQRgaAdNfAFoCEdAnjUVV94NZ3V9lChoBkdATQfdAPd2xWgHS81oCEdAnjdcnuy/sXV9lChoBkdAcEOcpb2US2gHTbQBaAhHQJ45s0l7dBV1fZQoaAZHQEpcJXyRSxZoB0vdaAhHQJ46+VW0Z3t1fZQoaAZHQG+6DJ2dNFloB01WAWgIR0CePg7HQyAQdX2UKGgGR0BIO4UnG828aAdL7GgIR0CeP1VJtix3dX2UKGgGR0BbcVV5rxiHaAdN6ANoCEdAnka4+8oQWnV9lChoBkdAb6PRdhRZU2gHTWcBaAhHQJ5JGQ3gk1N1fZQoaAZHQG9mtBF/hEVoB00gAmgIR0CeTv/X5FgEdX2UKGgGR0Bxr8DRtxdZaAdNSQFoCEdAnlDAjUutfXV9lChoBkdAcgHkwN9YwWgHTWMBaAhHQJ5SsGmk30h1fZQoaAZHQHJVnZkCmuVoB02HAWgIR0CeVfzBAOawdX2UKGgGR0BtsL8UEgW8aAdNiwFoCEdAnlgeIhyKenV9lChoBkdAbHhNliBoVWgHTXABaAhHQJ5bSP2f0291fZQoaAZHQHAUxxtHhCNoB03CAWgIR0CeXbFGXokidX2UKGgGR0BxNeBI4EOiaAdNUwFoCEdAnl+JHI6sAHV9lChoBkdAOObKV6eGwmgHTSoBaAhHQJ5iSISDh991fZQoaAZHQHFcxHLA57xoB01wAWgIR0CeZFCkXUH6dX2UKGgGR0BO+b6guh9LaAdL7GgIR0CeZZkfs/pudX2UKGgGR0BvXND6WPcSaAdNkAFoCEdAnmj3E61b7nV9lChoBkdAcjzGgBcRlGgHTQQBaAhHQJ5qWl54W1t1fZQoaAZHQHDXNdVvMr5oB01fAWgIR0CebEkz41xbdX2UKGgGR0BxOsS/TLGJaAdNhgFoCEdAnm+GH1vl2nV9lChoBkdAbs4qoZQ53mgHTV4BaAhHQJ5xbfTCtRx1fZQoaAZHQHFwweV9nbtoB01QAWgIR0CeczpcHGCJdX2UKGgGR0BswZ7eEZivaAdNZgFoCEdAnnZJs0pEyHV9lChoBkfAIhRQzk6tDGgHTRMBaAhHQJ54JhScbzd1fZQoaAZHQHEfcz2vjfhoB001AWgIR0CeekWGRFI/dX2UKGgGR0Btyrv9cbBHaAdNfQFoCEdAnn5+ryUcGXV9lChoBkdAbn2uCf6Gg2gHTf8BaAhHQJ6CWCcwxnF1fZQoaAZHQG1ydeQdS2poB01QAWgIR0CehBsXBP9DdX2UKGgGR0BwScy57PY4aAdNfAFoCEdAnodj2i+L33V9lChoBkdAcB2i1RceKmgHTWYBaAhHQJ6Jc8B+4LF1fZQoaAZHQHBpObVjI7xoB01XAWgIR0Cei0V5rxiHdX2UKGgGR0Bw7wDklu3uaAdNRgFoCEdAno48Pz4DcXV9lChoBkdAcKIfNzKcNGgHTTcBaAhHQJ6P7KfWcz91fZQoaAZHQG8gh/Aj6epoB01PAWgIR0Cekbxd6cAjdX2UKGgGR0A5OcxCY1HfaAdNCgFoCEdAnpRGqDK5kXV9lChoBkdAQRCBmPHT7WgHTRMBaAhHQJ6VyXw9aEB1fZQoaAZHQHBktGViWmhoB01TAWgIR0Cel485CF9KdX2UKGgGR0BFVHSfDk2haAdNHgFoCEdAnpkcpgCwKXV9lChoBkdAcWvS39aUzWgHTR4BaAhHQJ6bz212JSB1fZQoaAZHQGtRMiKR+0BoB00qAmgIR0CentJNj9XLdWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 3908,
+    "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "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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"
+    }
+}

ppo-LunarLander-v2-Shahzeb/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafa63939c9de525bd904ebddcf2899dd12e6ce21a2592c5fae6916677049b89
+size 88362

ppo-LunarLander-v2-Shahzeb/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0bada3a8d03300766154165db2c27d88505f98b8589d902295f15102406e6d
+size 43762

ppo-LunarLander-v2-Shahzeb/pytorch_variables.pth

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

ppo-LunarLander-v2-Shahzeb/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.11.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.5.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 3.1.0
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 240.83384980955196, "std_reward": 64.63159577633958, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-19T07:21:16.965925"}