arodriguez
commited on
Commit
•
18983fc
1
Parent(s):
38fab1b
Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 212.51 +/- 68.99
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
config.json
ADDED
@@ -0,0 +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 0x7fd9d60fa950>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd9d60fa9e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd9d60faa70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd9d60fab00>", "_build": "<function ActorCriticPolicy._build at 0x7fd9d60fab90>", "forward": "<function ActorCriticPolicy.forward at 0x7fd9d60fac20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd9d60facb0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd9d60fad40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd9d60fadd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd9d60fae60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd9d60faef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd9d6136e40>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651919561.4172046, "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:": "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:": "gAWVeRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIuB0aFqMBYkCUhpRSlIwBbJRN6AOMAXSUR0B3sf8l5WzXdX2UKGgGaAloD0MIkIR9OwmSYECUhpRSlGgVTegDaBZHQHe1XHaN+9d1fZQoaAZoCWgPQwhWfa62YhlZwJSGlFKUaBVNFQJoFkdAd760Cih37nV9lChoBmgJaA9DCAmp29lXnj/AlIaUUpRoFUvvaBZHQHfCYJAt4A11fZQoaAZoCWgPQwgkDW5rC+s8wJSGlFKUaBVL+GgWR0B3yNpqREF4dX2UKGgGaAloD0MI/14KD5rtGcCUhpRSlGgVS9hoFkdAd9Uh4dIXj3V9lChoBmgJaA9DCNfc0f/ysmrAlIaUUpRoFU10AWgWR0B32YguAZsLdX2UKGgGaAloD0MIrroO1ZQBYUCUhpRSlGgVTegDaBZHQHf0ehCdBjZ1fZQoaAZoCWgPQwhxOV6B6FBUQJSGlFKUaBVN6ANoFkdAd/xQ9A5aNnV9lChoBmgJaA9DCGUaTS7G8DtAlIaUUpRoFU3oA2gWR0B4BzAvcrRTdX2UKGgGaAloD0MI2uVbH1bOYkCUhpRSlGgVTegDaBZHQHgTmknCwbF1fZQoaAZoCWgPQwjK4v4j040xwJSGlFKUaBVL8WgWR0B4FXATIvJzdX2UKGgGaAloD0MIuMzpshicYECUhpRSlGgVTegDaBZHQHgYTXSSeRR1fZQoaAZoCWgPQwgvUb01sIkzQJSGlFKUaBVLymgWR0B4b/1oQFs6dX2UKGgGaAloD0MIfZQRF4D3UUCUhpRSlGgVTegDaBZHQHiD/6CUX551fZQoaAZoCWgPQwjKU1bT9XJHQJSGlFKUaBVN6ANoFkdAeJYs5XEIgXV9lChoBmgJaA9DCIo73uS3WFdAlIaUUpRoFU3oA2gWR0B4wCq6vq1PdX2UKGgGaAloD0MI8FAU6BNlNECUhpRSlGgVS/NoFkdAeMTCjUNKAnV9lChoBmgJaA9DCHy3eeOkGFpAlIaUUpRoFU3oA2gWR0B4x4mVqveQdX2UKGgGaAloD0MIGZEotCwIZECUhpRSlGgVTegDaBZHQHkEOBQN0/51fZQoaAZoCWgPQwhuaTUk7g1RQJSGlFKUaBVN6ANoFkdAeQh9Htnf23V9lChoBmgJaA9DCE7TZwdcslxAlIaUUpRoFU3oA2gWR0B5FTtBv73xdX2UKGgGaAloD0MIXvdWJCYwYkCUhpRSlGgVTegDaBZHQHkZtmcvugJ1fZQoaAZoCWgPQwgdAHFXr1xNQJSGlFKUaBVN6ANoFkdAeSGp8WsRx3V9lChoBmgJaA9DCAVQjCyZu0tAlIaUUpRoFU3oA2gWR0B5NN8E3bVSdX2UKGgGaAloD0MIsmX5ugwPYECUhpRSlGgVTegDaBZHQHla1vhqCYl1fZQoaAZoCWgPQwidSZuqe35JQJSGlFKUaBVN6ANoFkdAeWdLkjopx3V9lChoBmgJaA9DCAjnU8cq8FNAlIaUUpRoFU3oA2gWR0B5dZWDHwPRdX2UKGgGaAloD0MIOkAwR4/HYECUhpRSlGgVTegDaBZHQHl3prYXfqJ1fZQoaAZoCWgPQwih2XVvRfZUQJSGlFKUaBVN6ANoFkdAeXrM0gr6L3V9lChoBmgJaA9DCM7HtaFi/2XAlIaUUpRoFU2DAWgWR0B5iKFj/dZadX2UKGgGaAloD0MI/RGGAUteV0CUhpRSlGgVTegDaBZHQHnTlCPZIxx1fZQoaAZoCWgPQwhZFeEmoxRaQJSGlFKUaBVN6ANoFkdAefsz1schknV9lChoBmgJaA9DCHS1FfvLl1tAlIaUUpRoFU3oA2gWR0B6KDGXHBDYdX2UKGgGaAloD0MIrYkFviJvYECUhpRSlGgVTegDaBZHQHos08JUo8Z1fZQoaAZoCWgPQwh8fa1LjbNcQJSGlFKUaBVN6ANoFkdAei+Sq2jO9nV9lChoBmgJaA9DCP7yyYrhgFpAlIaUUpRoFU3oA2gWR0B6ZPos7MgVdX2UKGgGaAloD0MIIGEYsOQqW0CUhpRSlGgVTegDaBZHQHpo9MK1G9Z1fZQoaAZoCWgPQwhG6j2VU3xjQJSGlFKUaBVN6ANoFkdAenTjASFoMHV9lChoBmgJaA9DCIbKv5ZXC2BAlIaUUpRoFU3oA2gWR0B6gX4fwI+odX2UKGgGaAloD0MIqYO8HkwlVkCUhpRSlGgVTegDaBZHQHqUtg8bJfZ1fZQoaAZoCWgPQwgtW+uLhFhYQJSGlFKUaBVN6ANoFkdAerkdeIEbHnV9lChoBmgJaA9DCCI17WKabTPAlIaUUpRoFU3oA2gWR0B6xVDhLoOhdX2UKGgGaAloD0MIlZ7pJcZPUUCUhpRSlGgVTegDaBZHQHrTh9srNGF1fZQoaAZoCWgPQwjDLR9JSSliQJSGlFKUaBVN6ANoFkdAetXVXV9WqHV9lChoBmgJaA9DCCdO7ncoUVJAlIaUUpRoFU3oA2gWR0B62PJeVs1sdX2UKGgGaAloD0MIChLb3QMjU0CUhpRSlGgVTegDaBZHQHrnAnc+JP91fZQoaAZoCWgPQwj2m4npQsBSQJSGlFKUaBVN6ANoFkdAeuieK8+Ro3V9lChoBmgJaA9DCOMz2T9PwUvAlIaUUpRoFUvGaBZHQHs2uMl1KXh1fZQoaAZoCWgPQwiLMhtkkkNeQJSGlFKUaBVN6ANoFkdAe1LNGmUGFHV9lChoBmgJaA9DCD4mUprNLWJAlIaUUpRoFU3oA2gWR0B7eWjQAuIzdX2UKGgGaAloD0MIuti0UgjATECUhpRSlGgVTegDaBZHQHt98lgMMJB1fZQoaAZoCWgPQwjcuMX83N9dQJSGlFKUaBVN6ANoFkdAe4CjkuHvdHV9lChoBmgJaA9DCHkgskgTUGbAlIaUUpRoFU1UA2gWR0B7nIxVQyh0dX2UKGgGaAloD0MIn+klxjJEU0CUhpRSlGgVTegDaBZHQHu1jDn/1g91fZQoaAZoCWgPQwjfGW1VEuNfQJSGlFKUaBVN6ANoFkdAe7kmyxA0K3V9lChoBmgJaA9DCFQAjGfQpF1AlIaUUpRoFU3oA2gWR0B7z5ATqSowdX2UKGgGaAloD0MI4xx1dFziWkCUhpRSlGgVTegDaBZHQHvhuIInjQ11fZQoaAZoCWgPQwjkSdI1E5xhQJSGlFKUaBVN6ANoFkdAfBEQtSQ5m3V9lChoBmgJaA9DCBtHrMWnoAVAlIaUUpRoFU0TAWgWR0B8HEEW69TQdX2UKGgGaAloD0MIgbT/AVb3YkCUhpRSlGgVTegDaBZHQHwe0IPbwjN1fZQoaAZoCWgPQwh2i8BY33tgQJSGlFKUaBVN6ANoFkdAfCDIatLcsXV9lChoBmgJaA9DCJ+USQ1tmFZAlIaUUpRoFU3oA2gWR0B8I9nVXmvGdX2UKGgGaAloD0MImZ8bmrKhWUCUhpRSlGgVTegDaBZHQHwxtNN8E3d1fZQoaAZoCWgPQwhHA3gLJNdfQJSGlFKUaBVN6ANoFkdAfDNbDuSfUXV9lChoBmgJaA9DCENznUZag1NAlIaUUpRoFU3oA2gWR0B8OKiBXjlxdX2UKGgGaAloD0MITU2CN6QuYkCUhpRSlGgVTegDaBZHQHyeNSIgvDh1fZQoaAZoCWgPQwi4V+atuiFZQJSGlFKUaBVN6ANoFkdAfMe5HVf/m3V9lChoBmgJaA9DCE2giEUMSF1AlIaUUpRoFU3oA2gWR0B8zGaw2VFAdX2UKGgGaAloD0MIK4TVWMImW0CUhpRSlGgVTegDaBZHQHzPSNbTtsx1fZQoaAZoCWgPQwhnmxvTE2NfQJSGlFKUaBVN6ANoFkdAfOtk8zQ/o3V9lChoBmgJaA9DCMkh4uZUpFpAlIaUUpRoFU3oA2gWR0B9A2LcbiqAdX2UKGgGaAloD0MI0R+aeXJ8YkCUhpRSlGgVTegDaBZHQH0GtCzC1qp1fZQoaAZoCWgPQwhWYwlrYwwqQJSGlFKUaBVL8WgWR0B9KF/oaDPGdX2UKGgGaAloD0MIwxA5fT28W0CUhpRSlGgVTegDaBZHQH0tJr56+nJ1fZQoaAZoCWgPQwjUf9b8eEdhQJSGlFKUaBVN6ANoFkdAfVo7jkuHvnV9lChoBmgJaA9DCKERbFx/QGBAlIaUUpRoFU3oA2gWR0B9ZUO7QLNOdX2UKGgGaAloD0MIz/boDfeUUECUhpRSlGgVTegDaBZHQH1nuearmyR1fZQoaAZoCWgPQwijWkQUk41WQJSGlFKUaBVN6ANoFkdAfWmn62v0RXV9lChoBmgJaA9DCCoaa39nn1hAlIaUUpRoFU3oA2gWR0B9bKYrrgO0dX2UKGgGaAloD0MISdv4ExV7YUCUhpRSlGgVTZMCaBZHQH1z9fw7T2F1fZQoaAZoCWgPQwgmN4qsNXxYQJSGlFKUaBVN6ANoFkdAfXmJbt7a7HV9lChoBmgJaA9DCLCSj90FU1RAlIaUUpRoFU3oA2gWR0B9evg3tKI0dX2UKGgGaAloD0MISYCaWrY8TUCUhpRSlGgVTegDaBZHQH1/1WCEpRZ1fZQoaAZoCWgPQwjrbwnAP35ZQJSGlFKUaBVN6ANoFkdAfeGkTpPhynV9lChoBmgJaA9DCNmwprIokl9AlIaUUpRoFU3oA2gWR0B+CfIEKVpsdX2UKGgGaAloD0MI/g5FgT6FUkCUhpRSlGgVTegDaBZHQH4Mmh24d6t1fZQoaAZoCWgPQwgc7bjh95RhQJSGlFKUaBVN6ANoFkdAfj+wT/Q0GnV9lChoBmgJaA9DCLovZ7YrEFpAlIaUUpRoFU3oA2gWR0B+Q0iFCb+cdX2UKGgGaAloD0MIIorJG2CWVECUhpRSlGgVTegDaBZHQH5nTC1qnFZ1fZQoaAZoCWgPQwhWZkrrb0FYQJSGlFKUaBVN6ANoFkdAfmw5rgwXZXV9lChoBmgJaA9DCKwCtRg87lZAlIaUUpRoFU3oA2gWR0B+mmmZVn27dX2UKGgGaAloD0MIOBJosKnjW0CUhpRSlGgVTegDaBZHQH6lXoC+10F1fZQoaAZoCWgPQwizmNh8XENkQJSGlFKUaBVN6ANoFkdAfqe5n13+uXV9lChoBmgJaA9DCBJqhlTRL2JAlIaUUpRoFU3oA2gWR0B+qaFbmlqKdX2UKGgGaAloD0MI647FNimOYECUhpRSlGgVTegDaBZHQH6sU2cawUx1fZQoaAZoCWgPQwjcm98wUbplQJSGlFKUaBVN6ANoFkdAfrOXHzYmLXV9lChoBmgJaA9DCHLChNGsZ1xAlIaUUpRoFU3oA2gWR0B+uM6FM7EHdX2UKGgGaAloD0MIuoEC7+T3XkCUhpRSlGgVTegDaBZHQH66ZpztCzF1fZQoaAZoCWgPQwhxAtNp3atgQJSGlFKUaBVN6ANoFkdAfr9/8l5WzXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:712245c85d583d6aecd2f9bd8933334d0151405700ce69f9bcb32eb4ef94ca02
|
3 |
+
size 144040
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
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 0x7fd9d60fa950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd9d60fa9e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd9d60faa70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd9d60fab00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fd9d60fab90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fd9d60fac20>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd9d60facb0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fd9d60fad40>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd9d60fadd0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd9d60fae60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd9d60faef0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fd9d6136e40>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
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": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651919561.4172046,
|
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": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
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": 124,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4386180a0d0129473e2fcb7384450ca666d404b55f655834ada04f71ff998af
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dea204b39a57b90c15ae6ba18e4081ba453a96d8734b927ac95482c2b57c44ad
|
3 |
+
size 43201
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f9ba67997aa3af67330620fd6ea31369dd7509d2a8e4f70181b38231ed9528
|
3 |
+
size 254003
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 212.50900957645837, "std_reward": 68.98924672440191, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T10:45:14.845676"}
|