Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2-ian.zip +3 -0
- ppo-LunarLander-v2-ian/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2-ian/data +95 -0
- ppo-LunarLander-v2-ian/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2-ian/policy.pth +3 -0
- ppo-LunarLander-v2-ian/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2-ian/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: 263.55 +/- 21.54
|
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 0x7f8a40d97940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8a40d979d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8a40d97a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8a40d97af0>", "_build": "<function ActorCriticPolicy._build at 0x7f8a40d97b80>", "forward": "<function ActorCriticPolicy.forward at 0x7f8a40d97c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8a40d97ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8a40d97d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8a40d97dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8a40d97e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8a40d97ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8a40d97f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8a40d99580>"}, "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": 1680160902292552327, "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:": "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"}, "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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2-ian.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7eafc1a821ba252990835dcc6742311da0de7bca36b57372205e397af8ac5a56
|
3 |
+
size 147421
|
ppo-LunarLander-v2-ian/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2-ian/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 0x7f8a40d97940>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8a40d979d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8a40d97a60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8a40d97af0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f8a40d97b80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f8a40d97c10>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8a40d97ca0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8a40d97d30>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f8a40d97dc0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8a40d97e50>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8a40d97ee0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8a40d97f70>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f8a40d99580>"
|
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": 1680160902292552327,
|
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:": "gAWVehAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIldOeknOEb0CUhpRSlIwBbJRNTQGMAXSUR0CaOH4CIUJwdX2UKGgGaAloD0MIu5f75OjAckCUhpRSlGgVTV4BaBZHQJo4tn9Nvfl1fZQoaAZoCWgPQwiit3h4T8ttQJSGlFKUaBVNJQFoFkdAmjjncL0BfnV9lChoBmgJaA9DCG2MnfCSDG5AlIaUUpRoFU2qAmgWR0CaOcvysjmkdX2UKGgGaAloD0MIaVa2D3lOZUCUhpRSlGgVTegDaBZHQJo6S09hZyN1fZQoaAZoCWgPQwjQXn089ItvQJSGlFKUaBVNUAFoFkdAmjrNnscABHV9lChoBmgJaA9DCPpDM08uYHFAlIaUUpRoFU02AWgWR0CaOx5hz/6wdX2UKGgGaAloD0MI/U6TGW/OakCUhpRSlGgVTSYBaBZHQJo7T1TR6Wx1fZQoaAZoCWgPQwg6sBwhA5NMQJSGlFKUaBVNHAFoFkdAmjvsHv+fiHV9lChoBmgJaA9DCNYcIJgjCmZAlIaUUpRoFU3oA2gWR0CaO/ZvUBn0dX2UKGgGaAloD0MIrvTabGz9cECUhpRSlGgVTZQBaBZHQJo8nTMJQch1fZQoaAZoCWgPQwgFbXL4pE9sQJSGlFKUaBVNKAFoFkdAmjz69f1Hv3V9lChoBmgJaA9DCPBuZYlOEXFAlIaUUpRoFU03AWgWR0CaPz0Kqn3tdX2UKGgGaAloD0MIe2ZJgJpib0CUhpRSlGgVTRoBaBZHQJo/tCUornV1fZQoaAZoCWgPQwidvp6vWfRsQJSGlFKUaBVNbgFoFkdAmkE4BV+7UXV9lChoBmgJaA9DCED5u3fUpm9AlIaUUpRoFU0zAWgWR0CaQaHsC1Z1dX2UKGgGaAloD0MIH9jxX6ClcUCUhpRSlGgVTTwBaBZHQJpCUaxX4j91fZQoaAZoCWgPQwj5FWu4yHJvQJSGlFKUaBVNYAFoFkdAmkJfgFX7tXV9lChoBmgJaA9DCAlrY+yEr05AlIaUUpRoFUv0aBZHQJpCi88La251fZQoaAZoCWgPQwhOtRZmoUBuQJSGlFKUaBVNTAFoFkdAmkLL7fpD/nV9lChoBmgJaA9DCDOpoQ0AOHFAlIaUUpRoFU0/AWgWR0CaQ4HbAUL2dX2UKGgGaAloD0MIwhIPKJvQcECUhpRSlGgVTTQBaBZHQJpEboRqXWx1fZQoaAZoCWgPQwg8FAX6BLJxQJSGlFKUaBVNJwFoFkdAmkWqdtl7MXV9lChoBmgJaA9DCKdYNQjzXm9AlIaUUpRoFU1IAWgWR0CaRcDpkf9xdX2UKGgGaAloD0MIwxA5fT0acECUhpRSlGgVTWkBaBZHQJpF8Irvsqt1fZQoaAZoCWgPQwjrUiP0s5FvQJSGlFKUaBVNNgFoFkdAmkY9aY/mknV9lChoBmgJaA9DCIcyVMXUy3BAlIaUUpRoFU06AWgWR0CaR0LbpNbkdX2UKGgGaAloD0MIlBPtKqTENECUhpRSlGgVS+loFkdAmke9utOmBXV9lChoBmgJaA9DCDfHuU04HG5AlIaUUpRoFU0+AWgWR0CaR+8f3evZdX2UKGgGaAloD0MIt5xLcVXEcECUhpRSlGgVTTEBaBZHQJpK7S9du511fZQoaAZoCWgPQwjUDRR4J65wQJSGlFKUaBVNPAFoFkdAmk5qEFnqV3V9lChoBmgJaA9DCOPFwhC5Xm1AlIaUUpRoFU0tAWgWR0CaUGmGM4tIdX2UKGgGaAloD0MIJxb4iu61b0CUhpRSlGgVTUEBaBZHQJpQitITXat1fZQoaAZoCWgPQwjikA2kC1RyQJSGlFKUaBVNHAFoFkdAmlC+GwiaAnV9lChoBmgJaA9DCIuLo3ITgHFAlIaUUpRoFU0HAWgWR0CaUSsQ/X5GdX2UKGgGaAloD0MIpwLuef6TcUCUhpRSlGgVTRYBaBZHQJpSVa8pTdd1fZQoaAZoCWgPQwhp/wOsVUpSQJSGlFKUaBVL42gWR0CaUtnw5NoKdX2UKGgGaAloD0MIGVkyx7KacUCUhpRSlGgVTZUBaBZHQJpUQjGDL8t1fZQoaAZoCWgPQwhPsWoQZk9wQJSGlFKUaBVNHAFoFkdAmlRxplBhQXV9lChoBmgJaA9DCDdUjPP3UXFAlIaUUpRoFU1NAWgWR0CaVRUR3/xUdX2UKGgGaAloD0MInpeKjbkacUCUhpRSlGgVTU0BaBZHQJpWnYWcjJN1fZQoaAZoCWgPQwgeiCzSRN9uQJSGlFKUaBVNJwFoFkdAmlhNroGIK3V9lChoBmgJaA9DCERtG0bBam9AlIaUUpRoFU0xAmgWR0CaWITeO4oadX2UKGgGaAloD0MIkE5d+SypbkCUhpRSlGgVTR0BaBZHQJpaXR/mT1V1fZQoaAZoCWgPQwhJTFDD98BwQJSGlFKUaBVNGgFoFkdAmluc2eg+QnV9lChoBmgJaA9DCNOHLqjv+m5AlIaUUpRoFU15AmgWR0CaXF8OTaCddX2UKGgGaAloD0MIJ4i6D0AVbkCUhpRSlGgVTSMBaBZHQJpcagbp/w11fZQoaAZoCWgPQwh5Vz1gnghvQJSGlFKUaBVNOAFoFkdAmlzgY+B6KXV9lChoBmgJaA9DCPPlBdhHWHBAlIaUUpRoFU0tAWgWR0CaXYrxy4nXdX2UKGgGaAloD0MIMErQXyiDcUCUhpRSlGgVTRUBaBZHQJpxY0dilSF1fZQoaAZoCWgPQwglPQytDhZyQJSGlFKUaBVNOQFoFkdAmnFhBRhttXV9lChoBmgJaA9DCAu0O6RYq3FAlIaUUpRoFU1kAmgWR0CacZcer+5wdX2UKGgGaAloD0MIQuvhy0RobUCUhpRSlGgVTS0BaBZHQJpx8xL0z0p1fZQoaAZoCWgPQwgkXwmkxCo3QJSGlFKUaBVL5WgWR0Cac0HU+cH4dX2UKGgGaAloD0MIb2dfedDycUCUhpRSlGgVTQkDaBZHQJp0MvvjOs11fZQoaAZoCWgPQwggQlw5e/psQJSGlFKUaBVNNwFoFkdAmnRMZccENnV9lChoBmgJaA9DCPfHe9VKnHFAlIaUUpRoFU08AWgWR0CadhEsasIWdX2UKGgGaAloD0MIbW+3JAc8QkCUhpRSlGgVS9toFkdAmnZS0ngHeXV9lChoBmgJaA9DCHIxBtbxQm1AlIaUUpRoFU0gAWgWR0CadtJZGKAKdX2UKGgGaAloD0MIGyrG+Zveb0CUhpRSlGgVTRUBaBZHQJp5VJ2+wkh1fZQoaAZoCWgPQwhwfVhvlHZxQJSGlFKUaBVNFwFoFkdAmno2vfTCtXV9lChoBmgJaA9DCHgOZahKU3BAlIaUUpRoFU1PAWgWR0CaekMzuWrwdX2UKGgGaAloD0MIYygn2lVfcUCUhpRSlGgVTRkBaBZHQJp6TWH1vl51fZQoaAZoCWgPQwhy32qdOJ1xQJSGlFKUaBVNQwFoFkdAmnpX+VC5VnV9lChoBmgJaA9DCI1/n3Hh+m5AlIaUUpRoFU0WAWgWR0Caemgl4TsZdX2UKGgGaAloD0MIwvwVMtcRcUCUhpRSlGgVTRMBaBZHQJp8K/UONHZ1fZQoaAZoCWgPQwgf9kIBWxhxQJSGlFKUaBVNVgFoFkdAmn00wi7kGXV9lChoBmgJaA9DCABxV69icnFAlIaUUpRoFU0wAWgWR0CafyZk078vdX2UKGgGaAloD0MIMzUJ3hAycECUhpRSlGgVTTcBaBZHQJp/TK0UoKF1fZQoaAZoCWgPQwiP+usVlp5wQJSGlFKUaBVNJQNoFkdAmoE+LNwBHXV9lChoBmgJaA9DCLppM04DtnFAlIaUUpRoFU0ZAmgWR0Caggojv/ipdX2UKGgGaAloD0MIrORjd0ETcECUhpRSlGgVTTcBaBZHQJqCT6vaDf51fZQoaAZoCWgPQwj+mxcnvuRxQJSGlFKUaBVNKgFoFkdAmoLE/0NBnnV9lChoBmgJaA9DCDdtxmmItW9AlIaUUpRoFU1kAWgWR0CahKUY8+zMdX2UKGgGaAloD0MIwFyLFqATckCUhpRSlGgVTR4BaBZHQJqFobADaGp1fZQoaAZoCWgPQwgHfH4YoXNuQJSGlFKUaBVNIAFoFkdAmocMx46fa3V9lChoBmgJaA9DCPnZyHXTEnJAlIaUUpRoFU00AWgWR0CaiBrqMWGidX2UKGgGaAloD0MIP+QtV79hcUCUhpRSlGgVTTwBaBZHQJqIZ9LHuJF1fZQoaAZoCWgPQwij5xa6EkJtQJSGlFKUaBVNTQFoFkdAmolqDCgsb3V9lChoBmgJaA9DCFezzvh+cHJAlIaUUpRoFU0AAWgWR0CaiWz8gpz+dX2UKGgGaAloD0MIfQbUm9EjbUCUhpRSlGgVTVYBaBZHQJqJp8ohIOJ1fZQoaAZoCWgPQwiV1XQ90apxQJSGlFKUaBVNKwFoFkdAmopHtKIznHV9lChoBmgJaA9DCHcwYp9AAHFAlIaUUpRoFU0MAWgWR0Cai4s/IKc/dX2UKGgGaAloD0MIa7bykv92bkCUhpRSlGgVTQoBaBZHQJqLmXUpd8l1fZQoaAZoCWgPQwiZKa2/JSJLQJSGlFKUaBVL/2gWR0CajNorWiDedX2UKGgGaAloD0MIlPlH3ySdZECUhpRSlGgVTegDaBZHQJqOMp2ECeV1fZQoaAZoCWgPQwj1K50PzzFxQJSGlFKUaBVNGwFoFkdAmo7EsOG0u3V9lChoBmgJaA9DCFX6CWe3s3BAlIaUUpRoFU0tAWgWR0CajvH7P6bfdX2UKGgGaAloD0MI0/iFV5Lqb0CUhpRSlGgVTTsBaBZHQJqPKn1nM+x1fZQoaAZoCWgPQwhy+nq+5spxQJSGlFKUaBVNNgFoFkdAmpCpiqhlDnV9lChoBmgJaA9DCLeb4JsmgG5AlIaUUpRoFU0NAWgWR0CakOns9jgAdX2UKGgGaAloD0MIxMw+j9HobkCUhpRSlGgVTRsBaBZHQJqR4tVaOgh1fZQoaAZoCWgPQwjYD7HBQilvQJSGlFKUaBVNUQFoFkdAmpIVDBuXNXV9lChoBmgJaA9DCLQiaqJPBHFAlIaUUpRoFU0lAWgWR0CakmMl1KXfdX2UKGgGaAloD0MI2NXkKatXRkCUhpRSlGgVS+5oFkdAmpL1qN6w+3V9lChoBmgJaA9DCCHkvP+P+W9AlIaUUpRoFU04AWgWR0Cak6DgIhQndX2UKGgGaAloD0MIIOwUqwbfckCUhpRSlGgVTQoBaBZHQJqT2q6vq1R1fZQoaAZoCWgPQwh8gVmhSKFwQJSGlFKUaBVNPQFoFkdAmpPpC0F8onV9lChoBmgJaA9DCCtoWmJlbGxAlIaUUpRoFU0vAWgWR0Cak/WgezUrdX2UKGgGaAloD0MIdSDrqVXHbkCUhpRSlGgVTVABaBZHQJqUO9pRGc51ZS4="
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 248,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
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 |
+
}
|
ppo-LunarLander-v2-ian/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e74a7e33441aa9c058844341f9eabf1251db2a283459eebd6f4c4fe8311847c0
|
3 |
+
size 87929
|
ppo-LunarLander-v2-ian/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:090d01b4ca83bec4ec637fdba8c2d1d58a7bfae03694ec3d94a9be44a292bb7a
|
3 |
+
size 43393
|
ppo-LunarLander-v2-ian/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-ian/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.9.16
|
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 (232 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 263.54902429909464, "std_reward": 21.539515140848476, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-30T08:24:33.346985"}
|