Upload PPO LunarLander-v2 trained agent
Browse files- README.md +16 -28
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/_stable_baselines3_version +1 -1
- ppo-LunarLander-v2/data +49 -44
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +9 -7
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- LunarLander-v2
|
4 |
-
- ppo
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
-
-
|
8 |
-
- deep-rl-course
|
9 |
model-index:
|
10 |
- name: PPO
|
11 |
results:
|
@@ -17,33 +16,22 @@ model-index:
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
-
value:
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
24 |
|
25 |
-
|
|
|
|
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
'vf_coef': 0.5
|
38 |
-
'ent_coef': 0.01
|
39 |
-
'clip_coef': 0.2
|
40 |
-
'clip_vloss': True
|
41 |
-
'num_steps': 128
|
42 |
-
'learning_rate': 0.00025
|
43 |
-
'gae': True
|
44 |
-
'gamma': 0.99
|
45 |
-
'gae_lambda': 0.95
|
46 |
-
'num_minibatches': 8
|
47 |
-
'update_epochs': 4}
|
48 |
-
```
|
49 |
-
|
|
|
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:
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 263.16 +/- 22.38
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f866716e5e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f866716e670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f866716e700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f866716e790>", "_build": "<function ActorCriticPolicy._build at 0x7f866716e820>", "forward": "<function ActorCriticPolicy.forward at 0x7f866716e8b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f866716e940>", "_predict": "<function ActorCriticPolicy._predict at 0x7f866716e9d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f866716ea60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f866716eaf0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f866716eb80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f8667165e40>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670828368340921927, "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:": "gAWVZxAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIrOC3IYbFcECUhpRSlIwBbJRN+gKMAXSUR0CTFnPI4lyBdX2UKGgGaAloD0MI/g+wVu28cECUhpRSlGgVTcgBaBZHQJMW2armyPd1fZQoaAZoCWgPQwiM3NPVHSdvQJSGlFKUaBVNRwJoFkdAkxekvwmVq3V9lChoBmgJaA9DCDf92Y8UFW9AlIaUUpRoFU0TAWgWR0CTGFXumaYvdX2UKGgGaAloD0MIcSAkC5h+cECUhpRSlGgVTSIBaBZHQJMaJ+9alk91fZQoaAZoCWgPQwhE4EigQQdwQJSGlFKUaBVNNgFoFkdAkxpuw5eZ5XV9lChoBmgJaA9DCKIo0CeyTHFAlIaUUpRoFUvuaBZHQJMbk9eQdS51fZQoaAZoCWgPQwgfniXICDhwQJSGlFKUaBVNCgFoFkdAkxyducc2i3V9lChoBmgJaA9DCLOyfchb4HFAlIaUUpRoFU0gAWgWR0CTHMPci4axdX2UKGgGaAloD0MIZcdGIN7cb0CUhpRSlGgVTR0BaBZHQJMdYRsdkrh1fZQoaAZoCWgPQwjD76Zb9jpuQJSGlFKUaBVNfwFoFkdAkx17hegL7XV9lChoBmgJaA9DCEq3JXKBlXBAlIaUUpRoFUvWaBZHQJMd3X05EMN1fZQoaAZoCWgPQwi4VnvYy8pwQJSGlFKUaBVNUAFoFkdAkx5LR4QjEHV9lChoBmgJaA9DCEcBomDGcnFAlIaUUpRoFU0AAWgWR0CTHqjpcHGCdX2UKGgGaAloD0MIfJi9bHuKcECUhpRSlGgVTc8BaBZHQJMfm5lOGj91fZQoaAZoCWgPQwhD44kgzgpxQJSGlFKUaBVN2wFoFkdAkyDPYJ3PiXV9lChoBmgJaA9DCOny5nCtvXBAlIaUUpRoFU02AWgWR0CTIXqdH2AYdX2UKGgGaAloD0MIcVZETfQRQ0CUhpRSlGgVS8NoFkdAkyGaWom5UnV9lChoBmgJaA9DCCOFsvB1CnBAlIaUUpRoFU3vAWgWR0CTIpaya/h3dX2UKGgGaAloD0MI4xdeSfKQOMCUhpRSlGgVS8NoFkdAkyMumR/3FnV9lChoBmgJaA9DCP2iBP0FNG9AlIaUUpRoFU1cAWgWR0CTI2YdQwbmdX2UKGgGaAloD0MI34juWZcbckCUhpRSlGgVTecBaBZHQJMjh6iTMaF1fZQoaAZoCWgPQwiut81UyARwQJSGlFKUaBVL9WgWR0CTJAvq1PWQdX2UKGgGaAloD0MIherm4m/hcUCUhpRSlGgVTT4BaBZHQJMkK19fCyh1fZQoaAZoCWgPQwhpjxfSYQpxQJSGlFKUaBVNHwFoFkdAkyVtQwblzXV9lChoBmgJaA9DCJNS0O2ltXBAlIaUUpRoFU0fAWgWR0CTJhXN1QqJdX2UKGgGaAloD0MIGk0uxkBFcECUhpRSlGgVTQcBaBZHQJMmo7Rv3rV1fZQoaAZoCWgPQwiGWP0RhoVvQJSGlFKUaBVNpgFoFkdAkye77j1f3XV9lChoBmgJaA9DCA1Uxr9P721AlIaUUpRoFU09AWgWR0CTJ//T9bX6dX2UKGgGaAloD0MI9+gN95G7EkCUhpRSlGgVS7xoFkdAkypII8hcJXV9lChoBmgJaA9DCEp7gy9M0G9AlIaUUpRoFU1tAWgWR0CTK1UBGQS0dX2UKGgGaAloD0MIMbPPYxQTb0CUhpRSlGgVS/toFkdAkyt4BRyfc3V9lChoBmgJaA9DCDDWNzC5EXFAlIaUUpRoFU1FAWgWR0CTLCbKRuCPdX2UKGgGaAloD0MIPgYrTjUUcECUhpRSlGgVTcMBaBZHQJMsMTK1XvJ1fZQoaAZoCWgPQwhiLNMvUcFxQJSGlFKUaBVNqgFoFkdAky7plFtsN3V9lChoBmgJaA9DCM9pFmg3wnBAlIaUUpRoFU0rAWgWR0CTL7z7uUlidX2UKGgGaAloD0MIn69ZLtsucUCUhpRSlGgVTYsBaBZHQJMv2Ur08Nh1fZQoaAZoCWgPQwhnuAGfn2VtQJSGlFKUaBVNfgFoFkdAkzBOyE+PinV9lChoBmgJaA9DCOIFEanpFWxAlIaUUpRoFUv2aBZHQJMwV1FH8TB1fZQoaAZoCWgPQwiaJQFqardwQJSGlFKUaBVNAgFoFkdAkzD0waisXHV9lChoBmgJaA9DCF+0xwup1HBAlIaUUpRoFU1QAWgWR0CTMZqnFYMfdX2UKGgGaAloD0MIVBwHXi2ZcUCUhpRSlGgVS/ZoFkdAk0Yo6fapP3V9lChoBmgJaA9DCKg1zTsOC3NAlIaUUpRoFU1pAWgWR0CTRlvo/zJ7dX2UKGgGaAloD0MICFdAoZ5lbkCUhpRSlGgVTc4BaBZHQJNG6i1y/9J1fZQoaAZoCWgPQwjwayQJAuRwQJSGlFKUaBVNEAFoFkdAk0fgnx8UmHV9lChoBmgJaA9DCCAL0SEwVnJAlIaUUpRoFU0AAWgWR0CTR/t+TeO5dX2UKGgGaAloD0MIW+7MBIPNcUCUhpRSlGgVTQoCaBZHQJNILQ3PzFx1fZQoaAZoCWgPQwitodReRBxxQJSGlFKUaBVNIAFoFkdAk0jf/vOQhnV9lChoBmgJaA9DCDEkJxN3+nBAlIaUUpRoFUvjaBZHQJNKD+CK77N1fZQoaAZoCWgPQwijPPNyWP5yQJSGlFKUaBVNZgFoFkdAk0ohfrrxAnV9lChoBmgJaA9DCNrGn6isxXBAlIaUUpRoFU0SAWgWR0CTSp8uSOindX2UKGgGaAloD0MIdY4B2WvSb0CUhpRSlGgVTQkBaBZHQJNLAzpHI6t1fZQoaAZoCWgPQwhiwJKrWDZyQJSGlFKUaBVL8mgWR0CTS11e0G/vdX2UKGgGaAloD0MIgQcGED5oSUCUhpRSlGgVS8VoFkdAk0unskY4yXV9lChoBmgJaA9DCJCIKZGEGnBAlIaUUpRoFUvsaBZHQJNLxD+irT91fZQoaAZoCWgPQwj4pumzAzRyQJSGlFKUaBVNQgFoFkdAk0zk6T4cm3V9lChoBmgJaA9DCDYhrTGoUnFAlIaUUpRoFU0GAWgWR0CTTYcinpB5dX2UKGgGaAloD0MITBjNyvajQ0CUhpRSlGgVS9poFkdAk022ig00nHV9lChoBmgJaA9DCLU0t0KYY3JAlIaUUpRoFU0PAWgWR0CTTkoxHoX9dX2UKGgGaAloD0MIVaaYg2AIcECUhpRSlGgVTYYBaBZHQJNO0atLcsV1fZQoaAZoCWgPQwjjUSrhSeFwQJSGlFKUaBVL/2gWR0CTTuVvddmhdX2UKGgGaAloD0MIX3089N0ZUMCUhpRSlGgVTUsDaBZHQJNPL95yEL91fZQoaAZoCWgPQwj3BfTCHWxwQJSGlFKUaBVL9GgWR0CTT34wRGtqdX2UKGgGaAloD0MIPq946tFqckCUhpRSlGgVTU8BaBZHQJNRSSOinHh1fZQoaAZoCWgPQwh2b0VigrBtQJSGlFKUaBVL9GgWR0CTUUidrftQdX2UKGgGaAloD0MIBI9v75qxcUCUhpRSlGgVS/doFkdAk1J84ku6E3V9lChoBmgJaA9DCFd3LLbJy3FAlIaUUpRoFUv3aBZHQJNSnlYEGJN1fZQoaAZoCWgPQwhens4VZYRwQJSGlFKUaBVNIAFoFkdAk1MEeIVM23V9lChoBmgJaA9DCGTJHMu7dnBAlIaUUpRoFU1LAWgWR0CTU10wrUb2dX2UKGgGaAloD0MIB3qobYPzcECUhpRSlGgVTWgBaBZHQJNUJwfhddF1fZQoaAZoCWgPQwh3ZRcMLj5wQJSGlFKUaBVNQAFoFkdAk1RsSf16FHV9lChoBmgJaA9DCCuiJvo8gnBAlIaUUpRoFUv+aBZHQJNVFid8Rcx1fZQoaAZoCWgPQwiE8dO4N39uQJSGlFKUaBVNDAFoFkdAk1VQgLZzxXV9lChoBmgJaA9DCECH+fKCzHBAlIaUUpRoFU0/AWgWR0CTViNDtw71dX2UKGgGaAloD0MIZ195kF7PcUCUhpRSlGgVTRoBaBZHQJNWfQgLZzx1fZQoaAZoCWgPQwjqdYvAWExwQJSGlFKUaBVL/GgWR0CTVuHPeHi4dX2UKGgGaAloD0MI7DNnfUqTckCUhpRSlGgVTQsBaBZHQJNW+90zTF51fZQoaAZoCWgPQwhoImx4uhRxQJSGlFKUaBVNIQFoFkdAk1dIbsF+u3V9lChoBmgJaA9DCHYZ/tONgnFAlIaUUpRoFU0oAWgWR0CTV2Vx0dR0dX2UKGgGaAloD0MIkpc1sUAmbUCUhpRSlGgVTREBaBZHQJNZExIre691fZQoaAZoCWgPQwgZjuczoMhxQJSGlFKUaBVL8mgWR0CTWjVsUIszdX2UKGgGaAloD0MIrp0oCclucUCUhpRSlGgVTREBaBZHQJNaXwe/5+J1fZQoaAZoCWgPQwiyR6gZUjdwQJSGlFKUaBVNRgFoFkdAk1qvnSv1UXV9lChoBmgJaA9DCOCBAYTPznBAlIaUUpRoFUv0aBZHQJNbUxpL26F1fZQoaAZoCWgPQwjadARwM6VwQJSGlFKUaBVNMQFoFkdAk1u/91loUXV9lChoBmgJaA9DCIo5CDraBG1AlIaUUpRoFU0/AWgWR0CTW87f51vEdX2UKGgGaAloD0MInuv7cFD1cUCUhpRSlGgVTSEBaBZHQJNcUKkVN6B1fZQoaAZoCWgPQwhn7bYLDU9xQJSGlFKUaBVNEAFoFkdAk1zjX8O09nV9lChoBmgJaA9DCNCzWfX55XBAlIaUUpRoFU0LAWgWR0CTXdRplBhQdX2UKGgGaAloD0MIObUzTO26bkCUhpRSlGgVTREBaBZHQJNeWqyWzGB1fZQoaAZoCWgPQwhBDd/COnlvQJSGlFKUaBVNVQFoFkdAk16KBAfMfXV9lChoBmgJaA9DCBkfZi/bdERAlIaUUpRoFUvEaBZHQJNekKPXCj11fZQoaAZoCWgPQwjzzMthd+lxQJSGlFKUaBVNBgFoFkdAk16WhufmLnV9lChoBmgJaA9DCARY5NcPYXJAlIaUUpRoFU0nAWgWR0CTX0z7di2EdX2UKGgGaAloD0MI5rD7jmEKcECUhpRSlGgVTU8BaBZHQJNgDvkRzzV1fZQoaAZoCWgPQwgIy9jQTV9wQJSGlFKUaBVL/mgWR0CTYRAKv3ajdX2UKGgGaAloD0MI1qvI6MD4cUCUhpRSlGgVTZkBaBZHQJNhQMI/qxF1fZQoaAZoCWgPQwhp/S0BOKxwQJSGlFKUaBVL5GgWR0CTYWGy5Zr6dX2UKGgGaAloD0MINsmP+NXLcUCUhpRSlGgVTQIBaBZHQJNhlQyhzvJ1fZQoaAZoCWgPQwh1IsFUcxxxQJSGlFKUaBVNEAFoFkdAk2GkUsWfsnVlLg=="}, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f88ab1ea440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f88ab1ea4d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f88ab1ea560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f88ab1ea5f0>", "_build": "<function ActorCriticPolicy._build at 0x7f88ab1ea680>", "forward": "<function ActorCriticPolicy.forward at 0x7f88ab1ea710>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f88ab1ea7a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f88ab1ea830>", "_predict": "<function ActorCriticPolicy._predict at 0x7f88ab1ea8c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f88ab1ea950>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f88ab1ea9e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f88ab1eaa70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f88ab1e6400>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1685457369521308259, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
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 sha256:58303f51e2390eee72ad3386ca9cf50992bcc99f1509b72060722d439b11d3a6
|
3 |
+
size 146743
|
ppo-LunarLander-v2/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/data
CHANGED
@@ -3,60 +3,35 @@
|
|
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
|
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 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
-
"observation_space": {
|
24 |
-
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
-
":serialized:": "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",
|
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": 1015808,
|
46 |
"_total_timesteps": 1000000,
|
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:": "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"
|
56 |
-
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -67,15 +42,41 @@
|
|
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:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
"_n_updates": 248,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
@@ -86,9 +87,13 @@
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
93 |
-
"target_kl": null
|
|
|
|
|
|
|
|
|
94 |
}
|
|
|
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 use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f88ab1ea440>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f88ab1ea4d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f88ab1ea560>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f88ab1ea5f0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f88ab1ea680>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f88ab1ea710>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f88ab1ea7a0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f88ab1ea830>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f88ab1ea8c0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f88ab1ea950>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f88ab1ea9e0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f88ab1eaa70>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f88ab1e6400>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"num_timesteps": 1015808,
|
25 |
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1685457369521308259,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
|
|
|
|
|
|
|
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
"_current_progress_remaining": -0.015808000000000044,
|
45 |
+
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
"_n_updates": 248,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
|
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
}
|
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:f5f941988c6ac7d88c282cbbc8f41e793858d781a7e1b5ab87c3818ff3517ef9
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a28cfe914e84f2eb7926ab0b04ee16f649f1534c77e1b941925c9ec1ecb15383
|
3 |
+
size 43329
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
-
OS: Linux-5.
|
2 |
-
Python: 3.
|
3 |
-
Stable-Baselines3:
|
4 |
-
PyTorch:
|
5 |
-
GPU Enabled: True
|
6 |
-
Numpy: 1.
|
7 |
-
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
|
2 |
+
- Python: 3.10.11
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"mean_reward": 263.164422625885, "std_reward": 22.37531702534782, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-30T14:59:06.582911"}
|