SuperSecureHuman
commited on
Commit
•
0e90687
1
Parent(s):
edee32b
1M trained
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +22 -22
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 284.30 +/- 14.06
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
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 0x7f05bf3acb90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f05bf3acc20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f05bf3accb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f05bf3acd40>", "_build": "<function ActorCriticPolicy._build at 0x7f05bf3acdd0>", "forward": "<function ActorCriticPolicy.forward at 0x7f05bf3ace60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f05bf3acef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f05bf3acf80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f05bf3b2050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f05bf3b20e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f05bf3b2170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f05bf40b090>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVpQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoC0sIhZSMAUOUdJRSlIwEaGlnaJRoEyiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoC0sIhZRoFnSUUpSMDWJvdW5kZWRfYmVsb3eUaBMolggAAAAAAAAAAAAAAAAAAACUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBZ0lFKUjA1ib3VuZGVkX2Fib3ZllGgTKJYIAAAAAAAAAAAAAAAAAAAAlGgiSwiFlGgWdJRSlIwKX25wX3JhbmRvbZROdWIu", "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651719875.3267655, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVgBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMILpCg+HHNcECUhpRSlIwBbJRNaQGMAXSUR0CRUx5tFa0QdX2UKGgGaAloD0MIaRzqd2Gyb0CUhpRSlGgVTWsBaBZHQJFTg+bExZd1fZQoaAZoCWgPQwi9j6M5MoxtQJSGlFKUaBVNbAFoFkdAkVRZ5u63AnV9lChoBmgJaA9DCInRcwtdEnFAlIaUUpRoFU1QAWgWR0CRVMbQC0WudX2UKGgGaAloD0MI1v7O9ujab0CUhpRSlGgVTaQBaBZHQJFVyfnOjZd1fZQoaAZoCWgPQwjhCb3+JJ5tQJSGlFKUaBVNXgFoFkdAkVZYg3cYZXV9lChoBmgJaA9DCFdgyOoWc3FAlIaUUpRoFU2EAWgWR0CRbwHqNZNgdX2UKGgGaAloD0MI6GfqdUv3ckCUhpRSlGgVTUcBaBZHQJFvalANXo11fZQoaAZoCWgPQwipZ0Eo7/c1QJSGlFKUaBVNFwFoFkdAkW+TiwSrYHV9lChoBmgJaA9DCBlVhnH3wXBAlIaUUpRoFU1MAWgWR0CRcLb8FY+0dX2UKGgGaAloD0MICK2HLxOxckCUhpRSlGgVTWEBaBZHQJFwxU0elsR1fZQoaAZoCWgPQwgjgnFwaddyQJSGlFKUaBVNUAFoFkdAkXE02tMfzXV9lChoBmgJaA9DCGZLVkW46G1AlIaUUpRoFU1zAWgWR0CRcd1Oj7AMdX2UKGgGaAloD0MIfnIUIEqbcECUhpRSlGgVTUwBaBZHQJFyEhvBJqZ1fZQoaAZoCWgPQwh/LhoyXhByQJSGlFKUaBVNWgFoFkdAkXKBzBAOa3V9lChoBmgJaA9DCJgycEBLDG5AlIaUUpRoFU3EAWgWR0CRcywwCbMHdX2UKGgGaAloD0MI8parHxsobECUhpRSlGgVTVQBaBZHQJF0SLYPGyZ1fZQoaAZoCWgPQwjPS8XGvGFxQJSGlFKUaBVNcgFoFkdAkXS33L3bmHV9lChoBmgJaA9DCL5p+uyASHJAlIaUUpRoFU1CAWgWR0CRdNob4rSWdX2UKGgGaAloD0MI5xpmaPxkcECUhpRSlGgVTV0BaBZHQJF1JlMAWBV1fZQoaAZoCWgPQwhFYoIaPo5uQJSGlFKUaBVNPgFoFkdAkXXbQXyiEnV9lChoBmgJaA9DCM5Q3PEmNXBAlIaUUpRoFU1yAWgWR0CRdqhcqvvCdX2UKGgGaAloD0MI/I7hsR83bkCUhpRSlGgVTTIBaBZHQJF3KSNfgJl1fZQoaAZoCWgPQwihSWJJuWRrQJSGlFKUaBVNPwFoFkdAkXek1VHWjHV9lChoBmgJaA9DCG+df7vsbm5AlIaUUpRoFU13AWgWR0CReJU0vXbudX2UKGgGaAloD0MIvLGgMOgRcUCUhpRSlGgVTU8BaBZHQJF6l+z+m3x1fZQoaAZoCWgPQwiY273cJ7lwQJSGlFKUaBVNJQFoFkdAkXrr61stTXV9lChoBmgJaA9DCIHLY81IqXJAlIaUUpRoFU1UAWgWR0CRewf029+PdX2UKGgGaAloD0MIumbyzfZOcECUhpRSlGgVTUUBaBZHQJF7Iy8BdUt1fZQoaAZoCWgPQwgtl43OeYlwQJSGlFKUaBVNdgFoFkdAkXsh0dRzinV9lChoBmgJaA9DCKkvSzu1mHFAlIaUUpRoFU2jAWgWR0CRe99IwudxdX2UKGgGaAloD0MI0sWmlQJyckCUhpRSlGgVTcABaBZHQJF8kG/vfCR1fZQoaAZoCWgPQwhMVG8NLKhwQJSGlFKUaBVNLAFoFkdAkXy1LJ0W/XV9lChoBmgJaA9DCBU5RNycS2tAlIaUUpRoFU1CAWgWR0CRfNCfHxSYdX2UKGgGaAloD0MII/PIHwyXcECUhpRSlGgVTVwBaBZHQJF+KRuCPIZ1fZQoaAZoCWgPQwgc6+I2GoxyQJSGlFKUaBVNHQFoFkdAkX48p5NXYHV9lChoBmgJaA9DCPuSjQdbm3BAlIaUUpRoFU11AWgWR0CRfoCgsbvPdX2UKGgGaAloD0MIahX9oZmfR0CUhpRSlGgVS+1oFkdAkX71XiiqQ3V9lChoBmgJaA9DCJOrWPymR3BAlIaUUpRoFU1VAWgWR0CRgDpmEoOQdX2UKGgGaAloD0MImZoEb8h9cUCUhpRSlGgVTZYBaBZHQJGAfpcHGCJ1fZQoaAZoCWgPQwjknxnER35wQJSGlFKUaBVNjwFoFkdAkYKGNBF/hHV9lChoBmgJaA9DCCwujsrNX3FAlIaUUpRoFU0nAWgWR0CRgqenQ6ZIdX2UKGgGaAloD0MImj+mtWlfb0CUhpRSlGgVTS0BaBZHQJGDEhouf291fZQoaAZoCWgPQwjvAiUFVl1xQJSGlFKUaBVNZQFoFkdAkYTYvJzT4XV9lChoBmgJaA9DCC4B+KcU7XBAlIaUUpRoFU1lAWgWR0CRhU4X40uUdX2UKGgGaAloD0MIIxKFlrVjckCUhpRSlGgVTXUBaBZHQJGF9To+wC91fZQoaAZoCWgPQwhdixagbcRvQJSGlFKUaBVNYQFoFkdAkYZEMG5c1XV9lChoBmgJaA9DCA+0AkNWb29AlIaUUpRoFU1FAWgWR0CRhnL5hz/7dX2UKGgGaAloD0MI0VlmEYpDc0CUhpRSlGgVTQMBaBZHQJGGkhgVoHt1fZQoaAZoCWgPQwg6QZscPrNsQJSGlFKUaBVNQQFoFkdAkYhIB/7SA3V9lChoBmgJaA9DCA1slWBxOXFAlIaUUpRoFU2XAWgWR0CRiKb/Ot4idX2UKGgGaAloD0MIglX18jujcECUhpRSlGgVTT0BaBZHQJGI/LowEhd1fZQoaAZoCWgPQwhJTbuYZrBwQJSGlFKUaBVNRAFoFkdAkaKKkRBeHHV9lChoBmgJaA9DCEzeADPfXXBAlIaUUpRoFU2UAWgWR0CRouiSJTESdX2UKGgGaAloD0MIi+HqAAhWb0CUhpRSlGgVTfQBaBZHQJGjlum78Nx1fZQoaAZoCWgPQwiY2lIHOQtxQJSGlFKUaBVNdQFoFkdAkaRcOoYNzHV9lChoBmgJaA9DCNFZZhGKU29AlIaUUpRoFU1tAWgWR0CRptu6mO2idX2UKGgGaAloD0MIiNaKNodIcUCUhpRSlGgVTUQBaBZHQJGm2v5gw491fZQoaAZoCWgPQwjn4QSmE5lwQJSGlFKUaBVNQQFoFkdAkacqMefZmXV9lChoBmgJaA9DCCQNbmtLRXFAlIaUUpRoFU2HAWgWR0CRpzPe54GEdX2UKGgGaAloD0MIgGJkyVyxcECUhpRSlGgVTYgBaBZHQJGnVpfx+a11fZQoaAZoCWgPQwjwFHKlnm5vQJSGlFKUaBVNKwFoFkdAkaeWTPjXF3V9lChoBmgJaA9DCMCw/Pm2Am5AlIaUUpRoFU1RAWgWR0CRqFiKR+z/dX2UKGgGaAloD0MIVfZdEfxCcECUhpRSlGgVTW4BaBZHQJGpQuZkTYd1fZQoaAZoCWgPQwhgkV8/REJtQJSGlFKUaBVNOAFoFkdAkaneYlY2bXV9lChoBmgJaA9DCD1IT5FDBmxAlIaUUpRoFU0gAWgWR0CRq1XrMTvidX2UKGgGaAloD0MIoWZIFUUZcECUhpRSlGgVTWYBaBZHQJGrvrpqynl1fZQoaAZoCWgPQwgRyCWOPL5uQJSGlFKUaBVNnAFoFkdAkayOY+jdpXV9lChoBmgJaA9DCOF9VS4UcnBAlIaUUpRoFU09AWgWR0CRrSzlcQiBdX2UKGgGaAloD0MIyeU/pF/Sa0CUhpRSlGgVTf8BaBZHQJGtL8R+SbJ1fZQoaAZoCWgPQwj3x3vVSqtvQJSGlFKUaBVNbQFoFkdAka3ZXEIgNnV9lChoBmgJaA9DCOli00ohlm5AlIaUUpRoFU1IAWgWR0CRrh1g6U7kdX2UKGgGaAloD0MIH6D7cqa5cECUhpRSlGgVTRsBaBZHQJGu3iNsFdN1fZQoaAZoCWgPQwh4DI/97MlwQJSGlFKUaBVNIAFoFkdAka8BeXzDoHV9lChoBmgJaA9DCDmdZKvLZW1AlIaUUpRoFU1DAWgWR0CRsCLBsQ/YdX2UKGgGaAloD0MIv2A3bNsccECUhpRSlGgVTTcBaBZHQJGwMv6CUX51fZQoaAZoCWgPQwiy9Qzh2IlwQJSGlFKUaBVNUwFoFkdAkbCHWJ79h3V9lChoBmgJaA9DCDSdnQyOUnBAlIaUUpRoFU1BAWgWR0CRsRq6OHWSdX2UKGgGaAloD0MItp4hHPOacECUhpRSlGgVTYABaBZHQJGxsXSBshx1fZQoaAZoCWgPQwgiOZm4Vc1uQJSGlFKUaBVNZAFoFkdAkbLiA2AG0XV9lChoBmgJaA9DCIBJKlOMgnBAlIaUUpRoFU10AWgWR0CRtFgGr0aqdX2UKGgGaAloD0MIxOv6BbsFckCUhpRSlGgVTVIBaBZHQJG0uLKmsNl1fZQoaAZoCWgPQwifxyjPvGRwQJSGlFKUaBVNHwFoFkdAkbUm2LHdXXV9lChoBmgJaA9DCKM883JYxnBAlIaUUpRoFU1EAWgWR0CRtb1D0DlpdX2UKGgGaAloD0MIGEFjJhGWcECUhpRSlGgVTWsBaBZHQJG2KoGY8dR1fZQoaAZoCWgPQwgNxR1vcnRvQJSGlFKUaBVNLwFoFkdAkbavjfek6HV9lChoBmgJaA9DCKsGYW435HBAlIaUUpRoFU1GAWgWR0CRt5bvPToddX2UKGgGaAloD0MIca32sNc3ckCUhpRSlGgVTXwBaBZHQJG4GnbZezF1fZQoaAZoCWgPQwiXAPxTqlNtQJSGlFKUaBVNHgFoFkdAkbi0fPomonV9lChoBmgJaA9DCDZYOEnzDnBAlIaUUpRoFU0uAWgWR0CRuVIfr8iwdX2UKGgGaAloD0MIHvruVhZFcECUhpRSlGgVTW4BaBZHQJG50FTvRZ51fZQoaAZoCWgPQwhNMnIWdrpuQJSGlFKUaBVNUgFoFkdAkbrVs+FDfHV9lChoBmgJaA9DCIlDNpCuZmtAlIaUUpRoFU2gAWgWR0CRuy98qnWKdX2UKGgGaAloD0MIeCgK9Akjb0CUhpRSlGgVTWYBaBZHQJG8P6O5rgx1fZQoaAZoCWgPQwhmMbH5OK9wQJSGlFKUaBVNVwFoFkdAkbyOUhV2inV9lChoBmgJaA9DCInS3uCLUW1AlIaUUpRoFU1bAWgWR0CRvhqtozvadX2UKGgGaAloD0MIP6vMlNZVcECUhpRSlGgVTR0BaBZHQJG+GlANXo11fZQoaAZoCWgPQwgfSUkPQ3dwQJSGlFKUaBVNSwFoFkdAkb8mza9K3HV9lChoBmgJaA9DCNV46Saxw2xAlIaUUpRoFU07AWgWR0CRv4W3jMmndX2UKGgGaAloD0MIoPzdOypFckCUhpRSlGgVTTUBaBZHQJG/rFdcB2h1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "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 0x7f72feeafdd0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f72feeafe60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f72feeafef0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f72feeaff80>", "_build": "<function ActorCriticPolicy._build at 0x7f72feeb8050>", "forward": "<function ActorCriticPolicy.forward at 0x7f72feeb80e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f72feeb8170>", "_predict": "<function ActorCriticPolicy._predict at 0x7f72feeb8200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f72feeb8290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f72feeb8320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f72feeb83b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f72feef6d80>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "num_timesteps": 131072, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651729938.4875505, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.3107200000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1256, "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": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.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:dc9aa4f97b83ab05afbf94ee9ab87e8382c8194f89eef592d32eab20668d3620
|
3 |
+
size 144755
|
ppo-LunarLander-v2/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_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -41,13 +41,13 @@
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
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": {
|
@@ -56,26 +56,26 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
@@ -83,7 +83,7 @@
|
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
|
|
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 0x7f72feeafdd0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f72feeafe60>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f72feeafef0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f72feeaff80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f72feeb8050>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f72feeb80e0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f72feeb8170>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f72feeb8200>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f72feeb8290>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f72feeb8320>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f72feeb83b0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f72feef6d80>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
+
"n_envs": 32,
|
45 |
+
"num_timesteps": 131072,
|
46 |
+
"_total_timesteps": 100000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1651729938.4875505,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.3107200000000001,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 1256,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
+
"n_epochs": 8,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
ppo-LunarLander-v2/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 sha256:73c58f69d025196ebfc1c6eb64529e59c2562df382667833e48111af88283891
|
3 |
+
size 84893
|
ppo-LunarLander-v2/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:b2ba57c837f49a41b0b7d680d633ba5bbf2adb84261856d3f6f0d10d0495ae20
|
3 |
size 43201
|
replay.mp4
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 sha256:2e3687ad982202734859a8d2ca7ed63a18ec6f097e62177a9d3d05fd4996067f
|
3 |
+
size 203102
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 284.3023116646667, "std_reward": 14.062328295819668, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T05:56:30.625644"}
|