RL v2 LunarLander-v2 agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +21 -21
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- 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: 257.81 +/- 64.33
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7fcf5e03f200>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcf5e03f290>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcf5e03f320>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcf5e03f3b0>", "_build": "<function ActorCriticPolicy._build at 0x7fcf5e03f440>", "forward": "<function ActorCriticPolicy.forward at 0x7fcf5e03f4d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcf5e03f560>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcf5e03f5f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcf5e03f680>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcf5e03f710>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcf5e03f7a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcf5e0869f0>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 8, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670480186952804494, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gASV9QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGIvaG9tZS9qb2huZWJsYWtlL21hbWJhZm9yZ2UvZW52cy9zYjMvbGliL3B5dGhvbjMuNy9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMYi9ob21lL2pvaG5lYmxha2UvbWFtYmFmb3JnZS9lbnZzL3NiMy9saWIvcHl0aG9uMy43L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVjQEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwhLCIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUIAAQAAmhHluzZhSrxcwRO7C7KTO3KBvz0u/m28AACAPwAAgD/z6bc9yqkYP/LmLLzJ8Yu+GZaAPTvyNLwAAAAAAAAAAKqzdr70bKI/BY4Ov71T4r6b286+oHODvgAAAAAAAAAAmv34uxTshLpgNlw40dRVMzwtojqOZ4C3AACAPwAAgD8AsJO6OfZ0PhWcjzwT33m+X4lFvZESQTwAAAAAAAAAAOb1cT1xC6494yA4PpXxK74YItE9Z8/LPQAAAAAAAAAATW9fPQ1qfD/KJTc9r3nPvnFwzj3OaqG8AAAAAAAAAACa3y+8abZMPeIZGLv0Ahq+HpQzPX6xzzwAAAAAAAAAAJR0lGIu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVkAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwiFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYi4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVeRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMI3NRA8/kNcECUhpRSlIwBbJRNjAGMAXSUR0CaFldwNsnBdX2UKGgGaAloD0MINPPkmoKfbECUhpRSlGgVTSIBaBZHQJoXDYxtYSx1fZQoaAZoCWgPQwgVNgNckO5xQJSGlFKUaBVNQQFoFkdAmhpWAPNFB3V9lChoBmgJaA9DCPgcWI6Q+25AlIaUUpRoFU0nAWgWR0CaGw0bLlmwdX2UKGgGaAloD0MIjWMke4TBbkCUhpRSlGgVTUMBaBZHQJobYBYFJQN1fZQoaAZoCWgPQwiqYir9RJVyQJSGlFKUaBVNHAFoFkdAmht5KvmoznV9lChoBmgJaA9DCOrOE88ZLHFAlIaUUpRoFU1QAWgWR0CaHNohIOH4dX2UKGgGaAloD0MIjbYqiewWb0CUhpRSlGgVTTYBaBZHQJodGtwJgLJ1fZQoaAZoCWgPQwg/48KBkF5wQJSGlFKUaBVNawFoFkdAmh6RH09QoHV9lChoBmgJaA9DCKVlpN5Tk3BAlIaUUpRoFU1xAWgWR0CaH4/LkjoqdX2UKGgGaAloD0MINZpcjEFkc0CUhpRSlGgVS/9oFkdAmiDe3MINVnV9lChoBmgJaA9DCK8iowNS6nBAlIaUUpRoFU0tAWgWR0CaInU0vXbudX2UKGgGaAloD0MIdCSX/xDIcECUhpRSlGgVTWMBaBZHQJoisVYZEUl1fZQoaAZoCWgPQwguOllqfTpwQJSGlFKUaBVNQwFoFkdAmiLlDKHO8nV9lChoBmgJaA9DCCGRtvGnFG5AlIaUUpRoFU01AWgWR0CaJDrQgLZ0dX2UKGgGaAloD0MIi415HXFQckCUhpRSlGgVTUYBaBZHQJokYXaakRB1fZQoaAZoCWgPQwg656c4jpVxQJSGlFKUaBVNGwFoFkdAmiUXt8eCCnV9lChoBmgJaA9DCIc1lUXhyXJAlIaUUpRoFU0SAWgWR0CaNc1p0wJxdX2UKGgGaAloD0MI95Fbky7ucECUhpRSlGgVTS4BaBZHQJo3kFhXr+p1fZQoaAZoCWgPQwiCyY0iq59xQJSGlFKUaBVL/mgWR0CaOB3Dej20dX2UKGgGaAloD0MI6wJeZthucUCUhpRSlGgVTSMBaBZHQJo5OJGe+VV1fZQoaAZoCWgPQwiWJM/1PT9xQJSGlFKUaBVNOAFoFkdAmjlJ1eSjg3V9lChoBmgJaA9DCG7CvTKvAnJAlIaUUpRoFU0MAWgWR0CaOix7AtWddX2UKGgGaAloD0MIxOkkW13scUCUhpRSlGgVTR0BaBZHQJo6Y86mwaB1fZQoaAZoCWgPQwhlcf+R6ZNtQJSGlFKUaBVNFQFoFkdAmjr+jIq9XnV9lChoBmgJaA9DCAg57//jAG9AlIaUUpRoFU0TAWgWR0CaO6flZHNHdX2UKGgGaAloD0MIvK/KhcrJbkCUhpRSlGgVTS4BaBZHQJo+BZSvTw51fZQoaAZoCWgPQwgtCyb+KD5xQJSGlFKUaBVL/mgWR0CaPqEL6UJOdX2UKGgGaAloD0MIwhVQqGc0cECUhpRSlGgVTQUBaBZHQJo+ucFyJbd1fZQoaAZoCWgPQwi1No3t9S9wQJSGlFKUaBVNYAFoFkdAmj/EYGdI5HV9lChoBmgJaA9DCIfAkUCDL21AlIaUUpRoFU0+AWgWR0CaQVjB2wFDdX2UKGgGaAloD0MIdAzIXu/ybkCUhpRSlGgVTVIBaBZHQJpBl0PpY9x1fZQoaAZoCWgPQwi2n4zxYR1yQJSGlFKUaBVNKQFoFkdAmkGdrO7g9HV9lChoBmgJaA9DCHPXEvLBeHFAlIaUUpRoFU0/AWgWR0CaQshHLA58dX2UKGgGaAloD0MI0A1N2Wk8cECUhpRSlGgVTTUBaBZHQJpFMqwyIpJ1fZQoaAZoCWgPQwjH155ZEqlwQJSGlFKUaBVNGgFoFkdAmkVA5BC2MXV9lChoBmgJaA9DCIy8rImFl25AlIaUUpRoFU05AWgWR0CaRdS9/SYxdX2UKGgGaAloD0MIXwt6bwxbb0CUhpRSlGgVTRIBaBZHQJpHlKbrkbR1fZQoaAZoCWgPQwiAYmTJHBZxQJSGlFKUaBVNVwFoFkdAmkenZGrjpHV9lChoBmgJaA9DCMQGCyfpuG9AlIaUUpRoFU0fAWgWR0CaSBXg9/z8dX2UKGgGaAloD0MIopdRLHe3cUCUhpRSlGgVTS4BaBZHQJpIX4O+ZgJ1fZQoaAZoCWgPQwjYvKqz2pNsQJSGlFKUaBVNJQFoFkdAmklObd8ArHV9lChoBmgJaA9DCBU5RNyc+G1AlIaUUpRoFU03AWgWR0CaTEVmSQo1dX2UKGgGaAloD0MIrBvvjoyKbUCUhpRSlGgVTSsBaBZHQJpc5dD6WPd1fZQoaAZoCWgPQwgiGAeXDmtwQJSGlFKUaBVNTwFoFkdAml0QxBVuJnV9lChoBmgJaA9DCCJTPgQVAHFAlIaUUpRoFU0KAWgWR0CaXd7P6be/dX2UKGgGaAloD0MIIxXGFoI6cUCUhpRSlGgVTQgBaBZHQJpeX6dlNDd1fZQoaAZoCWgPQwhP6PUn8c1wQJSGlFKUaBVNIgFoFkdAml57xI8QqnV9lChoBmgJaA9DCPjGEACcxnBAlIaUUpRoFU0UAWgWR0CaXt2jfvWpdX2UKGgGaAloD0MIIJvkR/yvcECUhpRSlGgVTQMBaBZHQJpfcB0ZFXt1fZQoaAZoCWgPQwikqDP3EO1xQJSGlFKUaBVNLAFoFkdAmmMVJ17pmnV9lChoBmgJaA9DCIULeQQ3im9AlIaUUpRoFU0iAWgWR0CaYziwSrYHdX2UKGgGaAloD0MIXkpdMk4vcUCUhpRSlGgVTR0BaBZHQJpkNN/OMVF1fZQoaAZoCWgPQwjtEP+wZeNyQJSGlFKUaBVNCwFoFkdAmmRPPC2tuHV9lChoBmgJaA9DCF0WE5vPqnFAlIaUUpRoFU1NAWgWR0CaZH7di2DydX2UKGgGaAloD0MItI8V/PY3ckCUhpRSlGgVTS4BaBZHQJplKG1x82J1fZQoaAZoCWgPQwh+chQgCm5xQJSGlFKUaBVNJAFoFkdAmmVgQtjCpHV9lChoBmgJaA9DCJutvOS/OnBAlIaUUpRoFU0xAWgWR0CaZjJCSidrdX2UKGgGaAloD0MIkZxM3Oq9ckCUhpRSlGgVTQoBaBZHQJpop/vv0Ad1fZQoaAZoCWgPQwjZYOEkTQ1vQJSGlFKUaBVNQQFoFkdAmmo04Nqgy3V9lChoBmgJaA9DCHb+7bJfJnFAlIaUUpRoFU0bAWgWR0CaajXlKbrkdX2UKGgGaAloD0MIg8E1d/QRS0CUhpRSlGgVTRYBaBZHQJpqXv7WNFV1fZQoaAZoCWgPQwjBO/n0WO1uQJSGlFKUaBVNHwFoFkdAmmpmQ4jrzHV9lChoBmgJaA9DCIVDb/Ewm3BAlIaUUpRoFU0zAWgWR0Caa+k+otL+dX2UKGgGaAloD0MI/irAd1socUCUhpRSlGgVTRsBaBZHQJpsVL7Gecx1fZQoaAZoCWgPQwi5xmey/4FwQJSGlFKUaBVNXwFoFkdAmmyUwi7kGXV9lChoBmgJaA9DCD3wMVhxqhLAlIaUUpRoFUvpaBZHQJpvWgCfYjB1fZQoaAZoCWgPQwhcrKjBNGpwQJSGlFKUaBVL/WgWR0Cab6tEXtSidX2UKGgGaAloD0MIL26jAXyackCUhpRSlGgVS/5oFkdAmm+yq6vq1XV9lChoBmgJaA9DCI0pWONsP3BAlIaUUpRoFU0PAWgWR0CacDLS/j82dX2UKGgGaAloD0MILev+sVDLcUCUhpRSlGgVTVgBaBZHQJpwUFY+0PZ1fZQoaAZoCWgPQwjBUl3Ay8ptQJSGlFKUaBVNOwFoFkdAmnKh9srNGHV9lChoBmgJaA9DCFWgFoOHkXBAlIaUUpRoFU0fAWgWR0Cacr/zasZHdX2UKGgGaAloD0MINjrnpzi7bECUhpRSlGgVTTEBaBZHQJqC0BeXzDp1fZQoaAZoCWgPQwiDUrRyLxpuQJSGlFKUaBVNDwFoFkdAmoWNqpLmIXV9lChoBmgJaA9DCBPThVg9CHJAlIaUUpRoFU0QAWgWR0CahZxcmjTKdX2UKGgGaAloD0MItCH/zKAxcUCUhpRSlGgVTS8BaBZHQJqGCh7E5yV1fZQoaAZoCWgPQwhioGtfQMZyQJSGlFKUaBVNJQFoFkdAmobBiCrcTXV9lChoBmgJaA9DCEbPLXQlJVBAlIaUUpRoFUu+aBZHQJqG5ie/Yap1fZQoaAZoCWgPQwiSCI1g4zBwQJSGlFKUaBVNQAFoFkdAmocuavzOHHV9lChoBmgJaA9DCLVQMjn1LnBAlIaUUpRoFU0zAWgWR0CaiZssQNCrdX2UKGgGaAloD0MIKhvWVBb1bkCUhpRSlGgVTTkBaBZHQJqJofMfRu11fZQoaAZoCWgPQwg2Wg70kENxQJSGlFKUaBVNGwFoFkdAmoxfV7Qb/HV9lChoBmgJaA9DCJkqGJUUFHBAlIaUUpRoFU03AWgWR0CajJgZjx0/dX2UKGgGaAloD0MIT5DY7p6PckCUhpRSlGgVTQwBaBZHQJqM1DMNc4Z1fZQoaAZoCWgPQwhYHw999yFxQJSGlFKUaBVNQgFoFkdAmozlloUSI3V9lChoBmgJaA9DCBKHbCDdYXFAlIaUUpRoFU0RAWgWR0CajVYcvM8pdX2UKGgGaAloD0MIRluVRPbYb0CUhpRSlGgVTTsBaBZHQJqN24b0e2d1fZQoaAZoCWgPQwgLDi+ISHVyQJSGlFKUaBVNBQFoFkdAmo83V09yLnV9lChoBmgJaA9DCPAw7Zs7LHJAlIaUUpRoFU0aAWgWR0Caj6x8D0UXdX2UKGgGaAloD0MIa524HC+ZcECUhpRSlGgVTRkBaBZHQJqSj+wTufF1fZQoaAZoCWgPQwhqatla3/ByQJSGlFKUaBVL7GgWR0Cakw593KSxdX2UKGgGaAloD0MITN4AM9/ga0CUhpRSlGgVTTQBaBZHQJqTD3rUsnR1fZQoaAZoCWgPQwiWPnRBfdtvQJSGlFKUaBVNJgFoFkdAmpPK3AmAsnV9lChoBmgJaA9DCKEwKNOo83FAlIaUUpRoFU1OAWgWR0CalDIMBp6AdX2UKGgGaAloD0MIZCR7hJoDb0CUhpRSlGgVTV0BaBZHQJqUdBD5TIh1fZQoaAZoCWgPQwiTxmgdlSBwQJSGlFKUaBVNKgFoFkdAmpXzWCmMwXV9lChoBmgJaA9DCLdDw2JUt2xAlIaUUpRoFU0uAWgWR0CaloTGHYYjdX2UKGgGaAloD0MI7l2DvvQwc0CUhpRSlGgVTQUBaBZHQJqYPqVyFPB1fZQoaAZoCWgPQwgLQnkfhw5xQJSGlFKUaBVNAgFoFkdAmpiaGcnVonVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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-5.10.102.1-microsoft-standard-WSL2-x86_64-with-debian-bullseye-sid #1 SMP Wed Mar 2 00:30:59 UTC 2022", "Python": "3.7.12", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu117", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f15020a3cb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f15020a3d40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f15020a3dd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f15020a3e60>", "_build": "<function ActorCriticPolicy._build at 0x7f15020a3ef0>", "forward": "<function ActorCriticPolicy.forward at 0x7f15020a3f80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f15020a9050>", "_predict": "<function ActorCriticPolicy._predict at 0x7f15020a90e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f15020a9170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f15020a9200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f15020a9290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f15020e4e10>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670648843720080471, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVqAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSyCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDIAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAlHSUYi4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "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-5.10.102.1-microsoft-standard-WSL2-x86_64-with-debian-bullseye-sid #1 SMP Wed Mar 2 00:30:59 UTC 2022", "Python": "3.7.12", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu117", "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:fa8e0228ca91ede6350bb9408aadbebc1b53edf3c64df53399473fb6e682ae2b
|
3 |
+
size 148056
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,19 +4,19 @@
|
|
4 |
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
4 |
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f15020a3cb0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f15020a3d40>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f15020a3dd0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f15020a3e60>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f15020a3ef0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f15020a3f80>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f15020a9050>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f15020a90e0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f15020a9170>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f15020a9200>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f15020a9290>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f15020e4e10>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
+
"n_envs": 32,
|
45 |
+
"num_timesteps": 3014656,
|
46 |
+
"_total_timesteps": 3000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1670648843720080471,
|
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:": "gASVqAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSyCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDIAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAlHSUYi4="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.004885333333333408,
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 368,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
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 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54b6bf8a4b0b1a794556d3387298643614b9efbbd6e8583c7cec29750e65a2c2
|
3 |
size 87929
|
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 sha256:865174404ef6a0da5c12db42fc7a74171e3c8105adeff835175ad0489414267f
|
3 |
size 43201
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 257.8099568785143, "std_reward": 64.3270871430097, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-09T22:51:02.815533"}
|