init lunar lander v2 with ppo
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: 196.65 +/- 18.71
|
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 0x7f7629c25ef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7629c25f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7629c2b050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7629c2b0e0>", "_build": "<function ActorCriticPolicy._build at 0x7f7629c2b170>", "forward": "<function ActorCriticPolicy.forward at 0x7f7629c2b200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7629c2b290>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7629c2b320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7629c2b3b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7629c2b440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7629c2b4d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7629c75a50>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652082936.9070754, "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": 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:bb6b7547c2bb8cc220d6cac2c82e82ed99ed567b006a3c19ba898910ad6a12fd
|
3 |
+
size 144048
|
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 0x7f7629c25ef0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7629c25f80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7629c2b050>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7629c2b0e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f7629c2b170>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f7629c2b200>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7629c2b290>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f7629c2b320>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7629c2b3b0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7629c2b440>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7629c2b4d0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f7629c75a50>"
|
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": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1652082936.9070754,
|
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:": "gAWVgRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIvFruzARD/D+UhpRSlIwBbJRNSQGMAXSUR0CHNxAUtZmqdX2UKGgGaAloD0MIlNkgk4zGVECUhpRSlGgVTegDaBZHQIc8ALux8lZ1fZQoaAZoCWgPQwgpeuBjMM5hQJSGlFKUaBVN6ANoFkdAh0WYao/A03V9lChoBmgJaA9DCCxn74y2iVBAlIaUUpRoFU3oA2gWR0CHWpHcUM5PdX2UKGgGaAloD0MI0J1g//XnZUCUhpRSlGgVTegDaBZHQIda84cWCVd1fZQoaAZoCWgPQwi06J0KuKcVwJSGlFKUaBVNEgFoFkdAh1zWcawUxnV9lChoBmgJaA9DCGAEjZlEaF5AlIaUUpRoFU3oA2gWR0CHaSh7mdRSdX2UKGgGaAloD0MIbAcj9gkvYUCUhpRSlGgVTegDaBZHQIdptPFefI11fZQoaAZoCWgPQwg91owM8otgQJSGlFKUaBVN6ANoFkdAh7VfR3NcGHV9lChoBmgJaA9DCHtrYKsEYybAlIaUUpRoFU17AWgWR0CHvT04BFNMdX2UKGgGaAloD0MIrP9zmC8LW0CUhpRSlGgVTegDaBZHQIfDYb+98JF1fZQoaAZoCWgPQwjAWyBB8Us3wJSGlFKUaBVNHgFoFkdAh8RCFsYVI3V9lChoBmgJaA9DCPvOL0pQ02BAlIaUUpRoFU3oA2gWR0CHzhFS88LbdX2UKGgGaAloD0MIRtJu9LEyZUCUhpRSlGgVTegDaBZHQIfbNGZuyeJ1fZQoaAZoCWgPQwhbQ6m9iKRgQJSGlFKUaBVN6ANoFkdAh+MYPoV2zXV9lChoBmgJaA9DCJOrWPymM1pAlIaUUpRoFU3oA2gWR0CH8+x9G7SRdX2UKGgGaAloD0MInb6er1k6Y0CUhpRSlGgVTegDaBZHQIf330NBnjB1fZQoaAZoCWgPQwgm/FI/b/YzQJSGlFKUaBVNXAFoFkdAh/9sJpnHvXV9lChoBmgJaA9DCCLBVDNrcllAlIaUUpRoFU3oA2gWR0CIBOnHeaa1dX2UKGgGaAloD0MIRuwTQDESMMCUhpRSlGgVTWQBaBZHQIgJ/uTibUh1fZQoaAZoCWgPQwgv+3WnO69cQJSGlFKUaBVN6ANoFkdAiBZZDJEH+3V9lChoBmgJaA9DCBx4tdwZc2FAlIaUUpRoFU3oA2gWR0CIG1/bTMJQdX2UKGgGaAloD0MIJsXHJ2QUW0CUhpRSlGgVTegDaBZHQIg5nfO2RaJ1fZQoaAZoCWgPQwjhKHl1js5fQJSGlFKUaBVN6ANoFkdAiDn1e0G/vnV9lChoBmgJaA9DCCh/946apWBAlIaUUpRoFU3oA2gWR0CIR12ovSMMdX2UKGgGaAloD0MIIhlybD1gXUCUhpRSlGgVTegDaBZHQIhH4VARkEt1fZQoaAZoCWgPQwiR0JZzKeRfQJSGlFKUaBVN6ANoFkdAiJNcM3IdVHV9lChoBmgJaA9DCH/1uG81YmBAlIaUUpRoFU3oA2gWR0CIms/8EV32dX2UKGgGaAloD0MIKuCe588GYkCUhpRSlGgVTegDaBZHQIigvCbc45t1fZQoaAZoCWgPQwh+kGXBxCFAwJSGlFKUaBVNTgFoFkdAiKeY64lQdnV9lChoBmgJaA9DCO2A64oZ4SVAlIaUUpRoFU02AWgWR0CIscUr08NhdX2UKGgGaAloD0MIu3uA7svXXUCUhpRSlGgVTegDaBZHQIi4CRMewLV1fZQoaAZoCWgPQwivCWmNwdFgQJSGlFKUaBVN6ANoFkdAiL82o3rD63V9lChoBmgJaA9DCOwTQDGyBmFAlIaUUpRoFU3oA2gWR0CIz37OVxCIdX2UKGgGaAloD0MITFKZYo5LYECUhpRSlGgVTegDaBZHQIjTeFJxvNx1fZQoaAZoCWgPQwhagLbVLNhgQJSGlFKUaBVN6ANoFkdAiNr+M6zVt3V9lChoBmgJaA9DCFw65jxj72BAlIaUUpRoFU3oA2gWR0CI4HLvCuU2dX2UKGgGaAloD0MIgxYSMLrAXUCUhpRSlGgVTegDaBZHQIjlsGiYb851fZQoaAZoCWgPQwgLJCh+jKJaQJSGlFKUaBVN6ANoFkdAiPHSbpeNUHV9lChoBmgJaA9DCPJetTJhrmFAlIaUUpRoFU3oA2gWR0CI9szLOiWWdX2UKGgGaAloD0MIbLJGPUTJYECUhpRSlGgVTegDaBZHQIkVWIhyKel1fZQoaAZoCWgPQwgXmus00vJgQJSGlFKUaBVN6ANoFkdAiSR0utfXw3V9lChoBmgJaA9DCPaaHhQU7mNAlIaUUpRoFU3oA2gWR0CJO8CbMHKPdX2UKGgGaAloD0MIeGFrtvKQYUCUhpRSlGgVTegDaBZHQIl7NurIYFd1fZQoaAZoCWgPQwi4IjFBDRtaQJSGlFKUaBVN6ANoFkdAiYDLRrrPdHV9lChoBmgJaA9DCMOdCyM9oGNAlIaUUpRoFU3oA2gWR0CJh14iX6ZZdX2UKGgGaAloD0MIo1aYvleFYECUhpRSlGgVTegDaBZHQImQs6kqMFV1fZQoaAZoCWgPQwiR8L2/QaMlQJSGlFKUaBVNPgFoFkdAiZF9E9dNWXV9lChoBmgJaA9DCH9qvHQTEGBAlIaUUpRoFU3oA2gWR0CJld3g1m8NdX2UKGgGaAloD0MIsRTJVwJAXkCUhpRSlGgVTegDaBZHQImcQuh9LHx1fZQoaAZoCWgPQwgBwRw9fmNZQJSGlFKUaBVN6ANoFkdAiapOPmxMWXV9lChoBmgJaA9DCAHaVrPOGBBAlIaUUpRoFU3oA2gWR0CJra5WilBQdX2UKGgGaAloD0MIlsyxvCt3YECUhpRSlGgVTegDaBZHQIm0F47ihnJ1fZQoaAZoCWgPQwgtCVBTy7FdQJSGlFKUaBVN6ANoFkdAibjIAGSpznV9lChoBmgJaA9DCPN1Gf7TV11AlIaUUpRoFU3oA2gWR0CJvSp/gBLgdX2UKGgGaAloD0MIdEaU9gbmWkCUhpRSlGgVTegDaBZHQInH2zKLbYd1fZQoaAZoCWgPQwi9j6M5MtphQJSGlFKUaBVN6ANoFkdAicxnNorWiHV9lChoBmgJaA9DCOzAOSNK30lAlIaUUpRoFU3oA2gWR0CJ55GXokiVdX2UKGgGaAloD0MIzCpsBrhQHMCUhpRSlGgVTToBaBZHQIn+yIacZtN1fZQoaAZoCWgPQwjDuBtE679iQJSGlFKUaBVN6ANoFkdAig0MguAZsXV9lChoBmgJaA9DCKadmssNlFlAlIaUUpRoFU3oA2gWR0CKS/OZ9d/sdX2UKGgGaAloD0MIRmEXRQ+mY0CUhpRSlGgVTegDaBZHQIpR4a1kUbl1fZQoaAZoCWgPQwg3OXzSCadhQJSGlFKUaBVN6ANoFkdAilj0+kgwGnV9lChoBmgJaA9DCECIZMgx4WFAlIaUUpRoFU3oA2gWR0CKYsa0hNdrdX2UKGgGaAloD0MIAptz8ExvXECUhpRSlGgVTegDaBZHQIpjidDpkf91fZQoaAZoCWgPQwhig4WTNJ5dQJSGlFKUaBVN6ANoFkdAimgv8hs673V9lChoBmgJaA9DCMjShy6olGFAlIaUUpRoFU3oA2gWR0CKbssMAmzCdX2UKGgGaAloD0MIH4XrUbg/YECUhpRSlGgVTegDaBZHQIp9aioKlYV1fZQoaAZoCWgPQwgBipElc2tbQJSGlFKUaBVN6ANoFkdAioDknCwbEXV9lChoBmgJaA9DCN0/FqLD7GBAlIaUUpRoFU3oA2gWR0CKh5zS1E3LdX2UKGgGaAloD0MI+rmhKTulZECUhpRSlGgVTegDaBZHQIqMxdKNAC51fZQoaAZoCWgPQwjWq8jogD1lQJSGlFKUaBVN6ANoFkdAipGjd56dD3V9lChoBmgJaA9DCG78icqGNSZAlIaUUpRoFU0YAWgWR0CKkc4wRGtqdX2UKGgGaAloD0MIVpkprb9xM8CUhpRSlGgVTUkBaBZHQIqUQuAZsKt1fZQoaAZoCWgPQwjuCRLb3eM6wJSGlFKUaBVNcAFoFkdAipkC1RceKnV9lChoBmgJaA9DCHrjpDDv3mFAlIaUUpRoFU3oA2gWR0CKnIA3kxREdX2UKGgGaAloD0MIO+C6YkasQsCUhpRSlGgVTXgBaBZHQIq6c2YOUdJ1fZQoaAZoCWgPQwhv9DEfkKZgQJSGlFKUaBVN6ANoFkdAir5M6q8143V9lChoBmgJaA9DCLnhd9MtsVBAlIaUUpRoFU0bAWgWR0CKyvGVAzHkdX2UKGgGaAloD0MISn1Z2qljW0CUhpRSlGgVTegDaBZHQIrWEDyOJch1fZQoaAZoCWgPQwi4PNaMDCdlQJSGlFKUaBVNpgNoFkdAiuAMBQvYe3V9lChoBmgJaA9DCM3mcRhMxGBAlIaUUpRoFU3oA2gWR0CK46M5wOvudX2UKGgGaAloD0MIE2Iuqdq0ZECUhpRSlGgVTegDaBZHQIsndGiHqNZ1fZQoaAZoCWgPQwikUuxoHFRZQJSGlFKUaBVN6ANoFkdAiy6gwwj+rHV9lChoBmgJaA9DCGx4eqUs4WJAlIaUUpRoFU3oA2gWR0CLR89f1HvudX2UKGgGaAloD0MI2EXRAx/9Q8CUhpRSlGgVTVMBaBZHQItRaYiPhhp1fZQoaAZoCWgPQwiTqYJRyWlhQJSGlFKUaBVN6ANoFkdAi1o3+VC5VnV9lChoBmgJaA9DCD/h7Nay4GFAlIaUUpRoFU3oA2gWR0CLZ3Xr+o9+dX2UKGgGaAloD0MITE9Y4gFgX0CUhpRSlGgVTegDaBZHQItuIC0WuYB1fZQoaAZoCWgPQwit+8dCdORhQJSGlFKUaBVN6ANoFkdAi3Rm78Nx2nV9lChoBmgJaA9DCHiZYaOsultAlIaUUpRoFU3oA2gWR0CLdKBbOeJ6dX2UKGgGaAloD0MIYAK37uZrYkCUhpRSlGgVTegDaBZHQIt3uOCGvfV1fZQoaAZoCWgPQwivzFt1HZVZQJSGlFKUaBVN6ANoFkdAi32P9tMwlHV9lChoBmgJaA9DCLw9CAH5dFtAlIaUUpRoFU3oA2gWR0CLpbedCmdidX2UKGgGaAloD0MIh/iHLT0/XUCUhpRSlGgVTegDaBZHQIuqZ6KLsKN1fZQoaAZoCWgPQwgAjGfQ0NM0wJSGlFKUaBVNXwFoFkdAi7ESIYWLxnV9lChoBmgJaA9DCOnvpfCgJWJAlIaUUpRoFU3oA2gWR0CLuY6T4cm0dX2UKGgGaAloD0MInYU97fC7W0CUhpRSlGgVTegDaBZHQIvGPHaN+9d1fZQoaAZoCWgPQwjRXRJnRf9gQJSGlFKUaBVN6ANoFkdAi9Xh/RVp9XV9lChoBmgJaA9DCOyi6IGPfltAlIaUUpRoFU3oA2gWR0CL5N4dIXj3dWUu"
|
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:e6ec03aaee1be66bc3b5a38d88a7864e92dff64b49fa0d5ea510527967ffe17f
|
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:a78e13d64799cc097e4d93b9ac3d71256fc934abb3d3ed8071d02391e9d43ef9
|
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:dbaf70de67231ae43b239307e291e5909ec53ba986e56edb6445d8947ef792c8
|
3 |
+
size 255344
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 196.65259772985394, "std_reward": 18.714082302652038, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T08:25:39.070798"}
|