v0.1
Browse files- README.md +1 -1
- config.json +1 -1
- lunar-noob.zip +2 -2
- lunar-noob/data +26 -38
- lunar-noob/policy.optimizer.pth +2 -2
- lunar-noob/policy.pth +1 -1
- lunar-noob/system_info.txt +4 -4
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
type: LunarLander-v2
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value:
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 16 |
type: LunarLander-v2
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: -279.04 +/- 165.59
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
config.json
CHANGED
|
@@ -1 +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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f07bfa8d090>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f07bfa8d120>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f07bfa8d1b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f07bfa8d240>", "_build": "<function ActorCriticPolicy._build at 0x7f07bfa8d2d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f07bfa8d360>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f07bfa8d3f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f07bfa8d480>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f07bfa8d510>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f07bfa8d5a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f07bfa8d630>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f07bfa90b80>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "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", "n": 4, "_shape": [], "dtype": "int64", "_np_random": "RandomState(MT19937)"}, "n_envs": 1, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671943570936950610, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJpJ2zvcCG8+buZTPlzPTb7OvfS7mnOqvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0014719999999999178, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVchAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIdsb3xaVWMsCUhpRSlIwBbJRNrQGMAXSUR0ClpHTrE9+xdX2UKGgGaAloD0MI7x8L0SF5b0CUhpRSlGgVTUUBaBZHQKWlm5GSZBt1fZQoaAZoCWgPQwjZCpqWWCNaQJSGlFKUaBVN6ANoFkdApa1x3xFy73V9lChoBmgJaA9DCDOHpBZKhhjAlIaUUpRoFUv1aBZHQKWuO7q6e5F1fZQoaAZoCWgPQwjOUNzxJn/8v5SGlFKUaBVNJwFoFkdApa87R6Ww/3V9lChoBmgJaA9DCJXTnpJzk25AlIaUUpRoFU0gAWgWR0ClsCv2Xb/PdX2UKGgGaAloD0MIY2NeRxzIS0CUhpRSlGgVTegDaBZHQKW5DkpZwGZ1fZQoaAZoCWgPQwhqiCr8Gf4aQJSGlFKUaBVLyGgWR0Cluab2criEdX2UKGgGaAloD0MIy6FFtnMhaECUhpRSlGgVTa0BaBZHQKW7OsJY1YR1fZQoaAZoCWgPQwjdC8wKRXNTQJSGlFKUaBVN6ANoFkdApcBV7ngYQHV9lChoBmgJaA9DCNycSgaA2G9AlIaUUpRoFU1TAWgWR0ClxQVdgOSXdX2UKGgGaAloD0MINuSfGcQicECUhpRSlGgVTRwBaBZHQKXGBBtUGV11fZQoaAZoCWgPQwjRWPs728lKwJSGlFKUaBVL+mgWR0ClxtPAoG6gdX2UKGgGaAloD0MIkl7U7leNQsCUhpRSlGgVTQABaBZHQKXHpQBPsRh1fZQoaAZoCWgPQwhxrmGGRtplQJSGlFKUaBVNxQFoFkdApclo150KZ3V9lChoBmgJaA9DCNGRXP7DrW5AlIaUUpRoFU1gAWgWR0ClypLBCUosdX2UKGgGaAloD0MI3nahuU5BYMCUhpRSlGgVTbgBaBZHQKXPoTcIqsl1fZQoaAZoCWgPQwjJsIo3Mg5QQJSGlFKUaBVN6ANoFkdApdSCJyhi9nV9lChoBmgJaA9DCKHyr+WV3lHAlIaUUpRoFUuUaBZHQKXU8TqSowV1fZQoaAZoCWgPQwgJNq5/V0dgQJSGlFKUaBVN5gFoFkdApda4z3yqdnV9lChoBmgJaA9DCN2271F/00fAlIaUUpRoFUv3aBZHQKXbDGUfPop1fZQoaAZoCWgPQwg49BYPLwZwQJSGlFKUaBVNMQFoFkdApdwFbmlqJ3V9lChoBmgJaA9DCDvGFRfHz2FAlIaUUpRoFU2+AWgWR0Cl3ZoC2c8UdX2UKGgGaAloD0MIY5eo3hpNbUCUhpRSlGgVTVgBaBZHQKXeyWepXIV1fZQoaAZoCWgPQwjAl8KD5jlnQJSGlFKUaBVNIAFoFkdApd/JnBciW3V9lChoBmgJaA9DCAyQaAJFtV3AlIaUUpRoFU2rAWgWR0Cl4Ymce8wpdX2UKGgGaAloD0MIV7PO+L4ANMCUhpRSlGgVS9hoFkdApeW5YYBNmHV9lChoBmgJaA9DCKIpO/2gyVHAlIaUUpRoFUvzaBZHQKXmgSU1Q691fZQoaAZoCWgPQwgcCp+tg8RUwJSGlFKUaBVNBAFoFkdApedaB5HEuXV9lChoBmgJaA9DCGiR7Xw/j1bAlIaUUpRoFU1aAWgWR0Cl6HwBHTZydX2UKGgGaAloD0MIu9Bcp1ETckCUhpRSlGgVTfEBaBZHQKXqUw22oeh1fZQoaAZoCWgPQwjGMv0ScRNtQJSGlFKUaBVNNAFoFkdApetqMcZLqXV9lChoBmgJaA9DCBMsDme+o3BAlIaUUpRoFU0xAWgWR0Cl7HZTQ3PzdX2UKGgGaAloD0MIdVWgFoNjZUCUhpRSlGgVTdYCaBZHQKXzkcDr7fp1fZQoaAZoCWgPQwhNhXgkXmhSwJSGlFKUaBVNOwFoFkdApfSbxmTTv3V9lChoBmgJaA9DCJgZNsr6ClHAlIaUUpRoFU1JAWgWR0Cl9cBOYYzjdX2UKGgGaAloD0MII2jMJOoxRMCUhpRSlGgVTQcBaBZHQKX2mPn0TUR1fZQoaAZoCWgPQwgdWmQ736FXwJSGlFKUaBVNjgFoFkdApfgTkyULUnV9lChoBmgJaA9DCPXVVYFaSmDAlIaUUpRoFU1iAWgWR0Cl/MrIYFaCdX2UKGgGaAloD0MI4pNOJNgccECUhpRSlGgVTR4BaBZHQKX9u5R0lqt1fZQoaAZoCWgPQwjdzVMdcm5bwJSGlFKUaBVL6mgWR0Cl/neK8+RpdX2UKGgGaAloD0MIqOUHrvKPWkCUhpRSlGgVTegDaBZHQKYDjQHAymB1fZQoaAZoCWgPQwjLviuCf4JtQJSGlFKUaBVNPAFoFkdApgg3I8yN43V9lChoBmgJaA9DCFEWvr7WqTXAlIaUUpRoFUv+aBZHQKYJAJkXk5p1fZQoaAZoCWgPQwiwdakR+txtQJSGlFKUaBVNMAFoFkdApgoJy8zyjHV9lChoBmgJaA9DCOepDrkZKWNAlIaUUpRoFU2HAWgWR0CmC2+UILPVdX2UKGgGaAloD0MIFR3J5T9ORMCUhpRSlGgVTUsBaBZHQKYMgyzHCGh1fZQoaAZoCWgPQwgwgzEiUQVlQJSGlFKUaBVN6ANoFkdAphQlGViWmnV9lChoBmgJaA9DCAg7xapBTEDAlIaUUpRoFU2YAWgWR0CmFbawD/2kdX2UKGgGaAloD0MIu38sRIcYU8CUhpRSlGgVTRIBaBZHQKYWpBWxQi11fZQoaAZoCWgPQwgL7DGR0gpLwJSGlFKUaBVL42gWR0CmF1hq9GqhdX2UKGgGaAloD0MIZW6+Ed3xS8CUhpRSlGgVS7hoFkdAphfjKifxt3V9lChoBmgJaA9DCKAWg4dpn2NAlIaUUpRoFU2ZAWgWR0CmGW1sk6cRdX2UKGgGaAloD0MIn8iTpOvqb0CUhpRSlGgVTTEBaBZHQKYeBblA/s51fZQoaAZoCWgPQwiQpKSHoRRjQJSGlFKUaBVNTgFoFkdAph85iobXH3V9lChoBmgJaA9DCL9jeOxnJ25AlIaUUpRoFU00AWgWR0CmIDssH0K7dX2UKGgGaAloD0MITtAmh88bb0CUhpRSlGgVTTMBaBZHQKYhO+yJKrd1fZQoaAZoCWgPQwi9bhEYa7NkQJSGlFKUaBVNbAFoFkdApiKS+10DEHV9lChoBmgJaA9DCGx4eqWs8GBAlIaUUpRoFU0MAmgWR0CmJHN9YwIudX2UKGgGaAloD0MIp1g1CPN7a0CUhpRSlGgVTTkBaBZHQKYpFY4hllN1fZQoaAZoCWgPQwhtN8E3Ta5ZQJSGlFKUaBVNPgJoFkdApitixZ+x4nV9lChoBmgJaA9DCHjUmBDz7GFAlIaUUpRoFU3dAWgWR0CmLTjIBBAwdX2UKGgGaAloD0MIdelfksqsZkCUhpRSlGgVTVkBaBZHQKYubVYp2EF1fZQoaAZoCWgPQwipFDsaB3ltQJSGlFKUaBVNMAFoFkdApi9sGeMAFXV9lChoBmgJaA9DCLN6h9shVmZAlIaUUpRoFU0uAmgWR0CmNXvtMPBjdX2UKGgGaAloD0MIfEYiNIILV8CUhpRSlGgVTUMBaBZHQKY2k0waisZ1fZQoaAZoCWgPQwgvxOqPMLhpQJSGlFKUaBVNDAFoFkdApjd6nNxEOXV9lChoBmgJaA9DCDICKhxBC2RAlIaUUpRoFU3mAWgWR0CmOTF7dBSldX2UKGgGaAloD0MIwVQzaymAJcCUhpRSlGgVS+NoFkdApjnmd3B55nV9lChoBmgJaA9DCD230JUI5krAlIaUUpRoFU0kAWgWR0CmOuitzS1FdX2UKGgGaAloD0MIqpz2lJxCbECUhpRSlGgVTR0CaBZHQKZAnWAf+0h1fZQoaAZoCWgPQwjIYMWp1gxhQJSGlFKUaBVNbgFoFkdApkHyxeLNwHV9lChoBmgJaA9DCP7viApVHmFAlIaUUpRoFU1oAWgWR0CmQ1GQ0XP7dX2UKGgGaAloD0MIPNwODYsmYkCUhpRSlGgVTYYBaBZHQKZEveANG3F1fZQoaAZoCWgPQwgCS65i8fZuQJSGlFKUaBVNkgFoFkdApkYrVpblinV9lChoBmgJaA9DCN8bQwBwhm5AlIaUUpRoFU0XAWgWR0CmSqR5LRKIdX2UKGgGaAloD0MIzQaZZORLbECUhpRSlGgVTesBaBZHQKZMhc0tRN11fZQoaAZoCWgPQwjsFKsGYbVmQJSGlFKUaBVNWAFoFkdApk3IXGff43V9lChoBmgJaA9DCMR3YtaLdFhAlIaUUpRoFU3oA2gWR0CmUjB/y5I6dX2UKGgGaAloD0MI2dE41O89bkCUhpRSlGgVTS8BaBZHQKZWxqXWvr51fZQoaAZoCWgPQwhvZB75A6NtQJSGlFKUaBVNXwFoFkdAplfurGR3eXV9lChoBmgJaA9DCACsjhzpCmBAlIaUUpRoFU3oA2gWR0CmW/kKNQ0odX2UKGgGaAloD0MIAWpq2VqsbUCUhpRSlGgVTTYBaBZHQKZdC7T2FnJ1fZQoaAZoCWgPQwjFcHUAxFBiwJSGlFKUaBVNJwFoFkdApmGawD/2kHV9lChoBmgJaA9DCCb8Uj/vm29AlIaUUpRoFU0uAWgWR0CmYqMxoIv8dX2UKGgGaAloD0MIX0VGByQxI0CUhpRSlGgVS85oFkdApmNAr6LwWnV9lChoBmgJaA9DCG40gLdAXllAlIaUUpRoFU3oA2gWR0CmZ3KUeMhpdX2UKGgGaAloD0MIV68iowOCaECUhpRSlGgVTXYCaBZHQKZttKNAC4l1fZQoaAZoCWgPQwj+1k6UBCtvQJSGlFKUaBVNMwFoFkdApm60al1r7HV9lChoBmgJaA9DCPVnP1JELEHAlIaUUpRoFU0IAWgWR0Cmb5OoHcDbdX2UKGgGaAloD0MIxw4qcZ1EYUCUhpRSlGgVTfEBaBZHQKZxV6fJ3gV1fZQoaAZoCWgPQwiMLQQ5KG9EwJSGlFKUaBVNMAFoFkdApnJSDh99dHV9lChoBmgJaA9DCAtjC0EO1EfAlIaUUpRoFUu6aBZHQKZy3WnTAnF1fZQoaAZoCWgPQwiM22gAb0pbQJSGlFKUaBVNzAFoFkdApngbJU5uInV9lChoBmgJaA9DCIKsp1ZflmhAlIaUUpRoFU1YAWgWR0CmeUrWqcVhdX2UKGgGaAloD0MIu5o8ZbW3a0CUhpRSlGgVTbYDaBZHQKZ9zD63y7R1fZQoaAZoCWgPQwhDPX0E/gpOQJSGlFKUaBVN6ANoFkdApoVcI7eVLXV9lChoBmgJaA9DCOTYeobwYmFAlIaUUpRoFU0AA2gWR0CmiJHiWE9MdX2UKGgGaAloD0MILV3BNmKVZ0CUhpRSlGgVTXIBaBZHQKaJ8QVbiZR1fZQoaAZoCWgPQwhSSDKrd69tQJSGlFKUaBVL92gWR0CmisVcD8tPdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4890, "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, "system_info": {"OS": "Linux-6.0.12-76060006-generic-x86_64-with-glibc2.35 #202212290932~1671652965~22.04~452ea9d SMP PREEMPT_DYNAMIC Wed D", "Python": "3.10.8", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}
|
|
|
|
| 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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7fc00f15c550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc00f15c5e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc00f15c670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc00f15c700>", "_build": "<function ActorCriticPolicy._build at 0x7fc00f15c790>", "forward": "<function ActorCriticPolicy.forward at 0x7fc00f15c820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc00f15c8b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc00f15c940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc00f15c9d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc00f15ca60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc00f15caf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc00f4d4640>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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, "system_info": {"OS": "Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 #1 SMP Wed Mar 2 00:30:59 UTC 2022", "Python": "3.9.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.1", "Gym": "0.21.0"}}
|
lunar-noob.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:202930c66afed3b19ee0d36d7b40089b64cf2bfd97de29ee2159c49e583dc276
|
| 3 |
+
size 53051
|
lunar-noob/data
CHANGED
|
@@ -4,19 +4,19 @@
|
|
| 4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
| 5 |
"__module__": "stable_baselines3.common.policies",
|
| 6 |
"__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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 ",
|
| 7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
| 8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
| 9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
| 10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
| 11 |
-
"_build": "<function ActorCriticPolicy._build at
|
| 12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
| 13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
| 14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
| 15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
| 16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
| 17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
-
"_abc_impl": "<_abc._abc_data object at
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {},
|
|
@@ -35,47 +35,35 @@
|
|
| 35 |
},
|
| 36 |
"action_space": {
|
| 37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 38 |
-
":serialized:": "
|
| 39 |
"n": 4,
|
| 40 |
"_shape": [],
|
| 41 |
"dtype": "int64",
|
| 42 |
-
"_np_random":
|
| 43 |
},
|
| 44 |
-
"n_envs":
|
| 45 |
-
"num_timesteps":
|
| 46 |
-
"_total_timesteps":
|
| 47 |
"_num_timesteps_at_start": 0,
|
| 48 |
"seed": null,
|
| 49 |
"action_noise": null,
|
| 50 |
-
"start_time":
|
| 51 |
"learning_rate": 0.0003,
|
| 52 |
"tensorboard_log": null,
|
| 53 |
"lr_schedule": {
|
| 54 |
":type:": "<class 'function'>",
|
| 55 |
-
":serialized:": "
|
| 56 |
-
},
|
| 57 |
-
"_last_obs": {
|
| 58 |
-
":type:": "<class 'numpy.ndarray'>",
|
| 59 |
-
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJpJ2zvcCG8+buZTPlzPTb7OvfS7mnOqvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
| 60 |
-
},
|
| 61 |
-
"_last_episode_starts": {
|
| 62 |
-
":type:": "<class 'numpy.ndarray'>",
|
| 63 |
-
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
| 64 |
},
|
|
|
|
|
|
|
| 65 |
"_last_original_obs": null,
|
| 66 |
"_episode_num": 0,
|
| 67 |
"use_sde": false,
|
| 68 |
"sde_sample_freq": -1,
|
| 69 |
-
"_current_progress_remaining":
|
| 70 |
-
"ep_info_buffer":
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
},
|
| 74 |
-
"ep_success_buffer": {
|
| 75 |
-
":type:": "<class 'collections.deque'>",
|
| 76 |
-
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 77 |
-
},
|
| 78 |
-
"_n_updates": 4890,
|
| 79 |
"n_steps": 2048,
|
| 80 |
"gamma": 0.99,
|
| 81 |
"gae_lambda": 0.95,
|
|
@@ -86,7 +74,7 @@
|
|
| 86 |
"n_epochs": 10,
|
| 87 |
"clip_range": {
|
| 88 |
":type:": "<class 'function'>",
|
| 89 |
-
":serialized:": "
|
| 90 |
},
|
| 91 |
"clip_range_vf": null,
|
| 92 |
"normalize_advantage": true,
|
|
|
|
| 4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
| 5 |
"__module__": "stable_baselines3.common.policies",
|
| 6 |
"__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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 ",
|
| 7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fc00f15c550>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc00f15c5e0>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc00f15c670>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc00f15c700>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fc00f15c790>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fc00f15c820>",
|
| 13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc00f15c8b0>",
|
| 14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fc00f15c940>",
|
| 15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc00f15c9d0>",
|
| 16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc00f15ca60>",
|
| 17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc00f15caf0>",
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fc00f4d4640>"
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {},
|
|
|
|
| 35 |
},
|
| 36 |
"action_space": {
|
| 37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 38 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
| 39 |
"n": 4,
|
| 40 |
"_shape": [],
|
| 41 |
"dtype": "int64",
|
| 42 |
+
"_np_random": null
|
| 43 |
},
|
| 44 |
+
"n_envs": 16,
|
| 45 |
+
"num_timesteps": 0,
|
| 46 |
+
"_total_timesteps": 0,
|
| 47 |
"_num_timesteps_at_start": 0,
|
| 48 |
"seed": null,
|
| 49 |
"action_noise": null,
|
| 50 |
+
"start_time": null,
|
| 51 |
"learning_rate": 0.0003,
|
| 52 |
"tensorboard_log": null,
|
| 53 |
"lr_schedule": {
|
| 54 |
":type:": "<class 'function'>",
|
| 55 |
+
":serialized:": "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"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
},
|
| 57 |
+
"_last_obs": null,
|
| 58 |
+
"_last_episode_starts": null,
|
| 59 |
"_last_original_obs": null,
|
| 60 |
"_episode_num": 0,
|
| 61 |
"use_sde": false,
|
| 62 |
"sde_sample_freq": -1,
|
| 63 |
+
"_current_progress_remaining": 1,
|
| 64 |
+
"ep_info_buffer": null,
|
| 65 |
+
"ep_success_buffer": null,
|
| 66 |
+
"_n_updates": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"n_steps": 2048,
|
| 68 |
"gamma": 0.99,
|
| 69 |
"gae_lambda": 0.95,
|
|
|
|
| 74 |
"n_epochs": 10,
|
| 75 |
"clip_range": {
|
| 76 |
":type:": "<class 'function'>",
|
| 77 |
+
":serialized:": "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"
|
| 78 |
},
|
| 79 |
"clip_range_vf": null,
|
| 80 |
"normalize_advantage": true,
|
lunar-noob/policy.optimizer.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
|
| 3 |
+
size 687
|
lunar-noob/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43201
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b35e5a7c6a863e44cc662cad5f4e110a00a58f67ae8e217bb49bc92d83a592b2
|
| 3 |
size 43201
|
lunar-noob/system_info.txt
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
-
OS: Linux-
|
| 2 |
-
Python: 3.
|
| 3 |
Stable-Baselines3: 1.6.2
|
| 4 |
-
PyTorch: 1.
|
| 5 |
GPU Enabled: True
|
| 6 |
-
Numpy: 1.
|
| 7 |
Gym: 0.21.0
|
|
|
|
| 1 |
+
OS: Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 #1 SMP Wed Mar 2 00:30:59 UTC 2022
|
| 2 |
+
Python: 3.9.15
|
| 3 |
Stable-Baselines3: 1.6.2
|
| 4 |
+
PyTorch: 1.13.1+cu117
|
| 5 |
GPU Enabled: True
|
| 6 |
+
Numpy: 1.24.1
|
| 7 |
Gym: 0.21.0
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": -279.04060918593314, "std_reward": 165.5930482502335, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T08:32:21.583718"}
|