iiserkbikram
commited on
Commit
•
b67377f
1
Parent(s):
4ca0770
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +95 -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 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 251.43 +/- 45.68
|
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
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 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 0x7f3001030940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f30010309d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3001030a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3001030af0>", "_build": "<function ActorCriticPolicy._build at 0x7f3001030b80>", "forward": "<function ActorCriticPolicy.forward at 0x7f3001030c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3001030ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3001030d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3001030dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3001030e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3001030ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3001030f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f300102bde0>"}, "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": 1678281141295180237, "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:": "gAWVNBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIdJtwr8y0cUCUhpRSlIwBbJRL8owBdJRHQJ86ndTHbRF1fZQoaAZoCWgPQwgdHVcjezNxQJSGlFKUaBVL62gWR0CfOqoqkM1CdX2UKGgGaAloD0MIRn79ENsFcUCUhpRSlGgVS/doFkdAnztEvkBCD3V9lChoBmgJaA9DCI1HqYSn3HNAlIaUUpRoFUv3aBZHQJ87ibgCOm11fZQoaAZoCWgPQwg2VmKeVVdzQJSGlFKUaBVNHQFoFkdAnz8MKohpxnV9lChoBmgJaA9DCI46Oq5GO2NAlIaUUpRoFU3oA2gWR0CfP9NfPX05dX2UKGgGaAloD0MIAwZJnxY1c0CUhpRSlGgVS9doFkdAnz/mRJVbRnV9lChoBmgJaA9DCHTqymf5TW1AlIaUUpRoFUveaBZHQJ9ADpu/Dcd1fZQoaAZoCWgPQwj8witJXstwQJSGlFKUaBVLxmgWR0CfQPEwFkhBdX2UKGgGaAloD0MIcH1Yb9SocUCUhpRSlGgVS7poFkdAn0GkcwQDm3V9lChoBmgJaA9DCDCbAMMyHHBAlIaUUpRoFUvPaBZHQJ9CBvsJIDp1fZQoaAZoCWgPQwiBBMWPMSpxQJSGlFKUaBVL52gWR0CfQiWLxZuAdX2UKGgGaAloD0MIdCMsKqIicUCUhpRSlGgVS+toFkdAn0I6Mir1d3V9lChoBmgJaA9DCI5aYfpeIGVAlIaUUpRoFU3oA2gWR0CfRh+3pfQbdX2UKGgGaAloD0MIvwrw3aZ6cECUhpRSlGgVS8loFkdAn0bNgSeyzHV9lChoBmgJaA9DCPt1pzsPKHFAlIaUUpRoFUvoaBZHQJ9J3ICEHt51fZQoaAZoCWgPQwgyk6gXvJdwQJSGlFKUaBVL6mgWR0CfSj8UEgW8dX2UKGgGaAloD0MII93PKQggcUCUhpRSlGgVS/hoFkdAn0qfCEYfn3V9lChoBmgJaA9DCI9QM6TKC3JAlIaUUpRoFUvjaBZHQJ9LXq9oN/h1fZQoaAZoCWgPQwhXk6esJu1uQJSGlFKUaBVL2mgWR0CfS/puuRs/dX2UKGgGaAloD0MIFqdaC/MVckCUhpRSlGgVS+JoFkdAn01qkRBeHHV9lChoBmgJaA9DCFwdAHHX/XBAlIaUUpRoFUvvaBZHQJ9OAYj0L+h1fZQoaAZoCWgPQwh4Xio25uJiQJSGlFKUaBVN6ANoFkdAn05d+ocaO3V9lChoBmgJaA9DCNTWiGCc9GVAlIaUUpRoFU3oA2gWR0CfUqIS13MZdX2UKGgGaAloD0MIQplGk4tkYUCUhpRSlGgVTegDaBZHQJ9SxKXfIjp1fZQoaAZoCWgPQwhF1hpKLcVwQJSGlFKUaBVL52gWR0CfU2smfGuLdX2UKGgGaAloD0MIpIriVVYHcUCUhpRSlGgVS/poFkdAn1OqzVtoBnV9lChoBmgJaA9DCMvW+iIhAm5AlIaUUpRoFUvHaBZHQJ9U3VwxWT51fZQoaAZoCWgPQwjvrN12IbZxQJSGlFKUaBVL3mgWR0CfVlenyd4FdX2UKGgGaAloD0MIUb6ghcStcUCUhpRSlGgVS/JoFkdAn1asdHUc43V9lChoBmgJaA9DCNEksaRcGXBAlIaUUpRoFUvgaBZHQJ9XDbwjMV11fZQoaAZoCWgPQwiKk/sdioRuQJSGlFKUaBVL0WgWR0CfWC1YyO7ydX2UKGgGaAloD0MIIy2Vt6NUYUCUhpRSlGgVTegDaBZHQJ9YMGlhw2l1fZQoaAZoCWgPQwieeTnsPiZuQJSGlFKUaBVL1WgWR0CfWHtkFwDOdX2UKGgGaAloD0MIvM/x0SKScUCUhpRSlGgVTREBaBZHQJ9Zwrd30PJ1fZQoaAZoCWgPQwh5A8x8xy5yQJSGlFKUaBVNRAFoFkdAn1qB0lqrR3V9lChoBmgJaA9DCPuRIjJsEnFAlIaUUpRoFUvZaBZHQJ9bAaWHDaZ1fZQoaAZoCWgPQwgRV87emSNxQJSGlFKUaBVL92gWR0CfXEzhxYJWdX2UKGgGaAloD0MIEY/Ey1MJc0CUhpRSlGgVTRIBaBZHQJ9csUfxMFl1fZQoaAZoCWgPQwiPGaiM/3lhQJSGlFKUaBVN6ANoFkdAn1z/sNUfgnV9lChoBmgJaA9DCC0iiskb319AlIaUUpRoFU3oA2gWR0CfXbCUX531dX2UKGgGaAloD0MIKGN8mP0RcECUhpRSlGgVS+doFkdAn13pCv5gxHV9lChoBmgJaA9DCOvHJvkRGXRAlIaUUpRoFUv+aBZHQJ9eZEy+HrR1fZQoaAZoCWgPQwhJEK6AwotvQJSGlFKUaBVL2mgWR0CfXsCE6DGtdX2UKGgGaAloD0MIi96pgHvwbkCUhpRSlGgVS9loFkdAn18GaYu01XV9lChoBmgJaA9DCJFHcCPlDXJAlIaUUpRoFU0IAWgWR0CfXxsVclgMdX2UKGgGaAloD0MIkpGzsKdqb0CUhpRSlGgVS9FoFkdAn1/pjDsMRnV9lChoBmgJaA9DCGqHvyYrSXFAlIaUUpRoFU0VAWgWR0CfYEwRGtp3dX2UKGgGaAloD0MI6E6w/7otcECUhpRSlGgVS9BoFkdAn2CKY/mknHV9lChoBmgJaA9DCNJVurtObnBAlIaUUpRoFU2PAWgWR0CfYW/FirksdX2UKGgGaAloD0MIpfeNrz0TcUCUhpRSlGgVS+xoFkdAn2G8d92HL3V9lChoBmgJaA9DCP2H9NvXiXJAlIaUUpRoFUvXaBZHQJ9iVltj0+V1fZQoaAZoCWgPQwi8k0+PbdttQJSGlFKUaBVL0WgWR0CfYsio86mwdX2UKGgGaAloD0MIPWU1XY8Yc0CUhpRSlGgVS+xoFkdAn2NDxCpm3HV9lChoBmgJaA9DCK/RcqAHAG5AlIaUUpRoFUvYaBZHQJ9j0khRqGl1fZQoaAZoCWgPQwg2H9eGCuZuQJSGlFKUaBVL3WgWR0CfZHMmF8G+dX2UKGgGaAloD0MIa0dxjvqJcECUhpRSlGgVS81oFkdAn2S3yRSxaHV9lChoBmgJaA9DCJF8JZASC3JAlIaUUpRoFU0SAWgWR0CfZVFC9h7WdX2UKGgGaAloD0MIzTy5psADcECUhpRSlGgVS+doFkdAn2VnLNfPX3V9lChoBmgJaA9DCGhaYmU0O29AlIaUUpRoFUvTaBZHQJ9lzmZE2Hd1fZQoaAZoCWgPQwjp0r8kVdhwQJSGlFKUaBVNAQFoFkdAn2XalP8AJnV9lChoBmgJaA9DCK/sgsG1H3FAlIaUUpRoFUvQaBZHQJ9mJm16Vt51fZQoaAZoCWgPQwi2uwfovtZwQJSGlFKUaBVL92gWR0CfZ3TpPhybdX2UKGgGaAloD0MIpRKe0Cu1cUCUhpRSlGgVS+FoFkdAn2fKNuLrHHV9lChoBmgJaA9DCGU2yCQjA11AlIaUUpRoFU3oA2gWR0CfZ99Oh0yQdX2UKGgGaAloD0MIqOFbWHf5cUCUhpRSlGgVS8loFkdAn2gAjY7JXHV9lChoBmgJaA9DCLsO1ZRkU3JAlIaUUpRoFUv0aBZHQJ9oiFJxvNx1fZQoaAZoCWgPQwg2qz5X22hyQJSGlFKUaBVL72gWR0CfaVLWZqmCdX2UKGgGaAloD0MIBvaYSGlvckCUhpRSlGgVS+RoFkdAn2l7dadMCnV9lChoBmgJaA9DCPhVuVD50W1AlIaUUpRoFUvSaBZHQJ9qGAEt/Wl1fZQoaAZoCWgPQwgkgJvFiwduQJSGlFKUaBVL5WgWR0CfatR3/xUedX2UKGgGaAloD0MIC+9yEV+KcUCUhpRSlGgVS9BoFkdAn2rj8P4EfXV9lChoBmgJaA9DCD5eSIcHxXJAlIaUUpRoFUvVaBZHQJ9rcjt5UtJ1fZQoaAZoCWgPQwg6PITxk59wQJSGlFKUaBVL2WgWR0Cfa4M495hSdX2UKGgGaAloD0MIC7Q7pBi+cECUhpRSlGgVS8hoFkdAn2ylRYRuj3V9lChoBmgJaA9DCFa7JqR103JAlIaUUpRoFUv5aBZHQJ9sq4MF2V51fZQoaAZoCWgPQwhYqgt4GV5vQJSGlFKUaBVLw2gWR0CfbNIEKVpsdX2UKGgGaAloD0MIKjdRS/MkckCUhpRSlGgVS79oFkdAn2zLx/d69nV9lChoBmgJaA9DCAZINIGir3BAlIaUUpRoFUvIaBZHQJ9u0uPFNtZ1fZQoaAZoCWgPQwiNf59xoSZzQJSGlFKUaBVNCwFoFkdAn28GkWRA8nV9lChoBmgJaA9DCArWOJvOyXNAlIaUUpRoFUv+aBZHQJ9vRVrAP/d1fZQoaAZoCWgPQwgwR4/fG/VxQJSGlFKUaBVL/WgWR0CfcDIE8q4IdX2UKGgGaAloD0MIYp0q37OObUCUhpRSlGgVS8JoFkdAn3DXkLhJiHV9lChoBmgJaA9DCMwmwLB8VnBAlIaUUpRoFU0DAWgWR0CfcT6C17Y1dX2UKGgGaAloD0MI3BK54AyiZUCUhpRSlGgVTegDaBZHQJ9xQmeDnNh1fZQoaAZoCWgPQwg9gbBTLPduQJSGlFKUaBVL3mgWR0CfcbIwdsBRdX2UKGgGaAloD0MId6IkJFJ9cUCUhpRSlGgVS/toFkdAn3HG7nPmgnV9lChoBmgJaA9DCKH0hZAzt3BAlIaUUpRoFUu9aBZHQJ9x+EL6UJR1fZQoaAZoCWgPQwhFZi5wOYxxQJSGlFKUaBVLymgWR0Cfcntuk1uSdX2UKGgGaAloD0MIFoTyPo4IcECUhpRSlGgVTSUBaBZHQJ9y8JokAxV1fZQoaAZoCWgPQwgH6pRHt91xQJSGlFKUaBVL7WgWR0CfczO8kD6ndX2UKGgGaAloD0MIJVryeBqicECUhpRSlGgVTQwBaBZHQJ90EhTwUg11fZQoaAZoCWgPQwjfqBWm7ytxQJSGlFKUaBVLxWgWR0CfdFT3qRlpdX2UKGgGaAloD0MIxjAnaBPqcUCUhpRSlGgVS8BoFkdAn3RtQbdadXV9lChoBmgJaA9DCCgs8YCye29AlIaUUpRoFUvtaBZHQJ91GCK77Kt1fZQoaAZoCWgPQwi3lzRGKw1xQJSGlFKUaBVL5WgWR0CfdhNWU8msdX2UKGgGaAloD0MIahZod8i8bkCUhpRSlGgVS9doFkdAn3ZN5UtI1HV9lChoBmgJaA9DCEWeJF3zf3BAlIaUUpRoFUvVaBZHQJ92mWt2cKB1fZQoaAZoCWgPQwj+D7BWrQBxQJSGlFKUaBVLy2gWR0CfdsWN3np0dX2UKGgGaAloD0MIfEj43t/4b0CUhpRSlGgVS+BoFkdAn3bh2nsLOXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1babe1c00ce93f0451b5a925068a035477318a3f921adf8c8cbaa620db139ee0
|
3 |
+
size 147323
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 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 0x7f3001030940>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f30010309d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3001030a60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3001030af0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3001030b80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3001030c10>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3001030ca0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3001030d30>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3001030dc0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3001030e50>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3001030ee0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3001030f70>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f300102bde0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
+
"dtype": "float32",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1678281141295180237,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 310,
|
80 |
+
"n_steps": 2048,
|
81 |
+
"gamma": 0.99,
|
82 |
+
"gae_lambda": 0.95,
|
83 |
+
"ent_coef": 0.0,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b804e93dc9ab663bb97d1cb9c0f4b9a7c5b1aa76f0166bc207198fc6c3e44dc
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0079dac4dc1b3283c3dba7687210fe68cfca131cc809140e5f66a398ca964d8d
|
3 |
+
size 43393
|
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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (201 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 251.4267101624186, "std_reward": 45.681313864922544, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-08T14:17:46.968363"}
|