Upload first PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 253.72 +/- 20.52
|
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 0x7f4f3246bf80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f32474050>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f324740e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f32474170>", "_build": "<function ActorCriticPolicy._build at 0x7f4f32474200>", "forward": "<function ActorCriticPolicy.forward at 0x7f4f32474290>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f32474320>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4f324743b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f32474440>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f324744d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f32474560>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f4f324b2cf0>"}, "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": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651752416.9091294, "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": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 160, "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-5.4.188+-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:bf6e2037cc3b241804fed5bb729e9b602f6c3c7e74d864d6f398aea2ba7c5271
|
3 |
+
size 144094
|
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 0x7f4f3246bf80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f32474050>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f324740e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f32474170>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f4f32474200>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f4f32474290>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f32474320>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f4f324743b0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f32474440>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f324744d0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f32474560>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f4f324b2cf0>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 524288,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651752416.9091294,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
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": -0.04857599999999995,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 160,
|
79 |
+
"n_steps": 2048,
|
80 |
+
"gamma": 0.99,
|
81 |
+
"gae_lambda": 0.95,
|
82 |
+
"ent_coef": 0.0,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 10,
|
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 sha256:2b8f6c9bf5b0a37e55aceda6df3483b2df8e46e7d71d9904b21b41d1af7059a3
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5222f685a63806a0f1e5d44e53cd99f223ee1dd3e39085b6a903f3937d6c9020
|
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:ecc1924a5fc4037ddc09dae937f8f64efb6f7f4bd6fec729d8cb9f86e5764b95
|
3 |
+
size 199630
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 253.720642711849, "std_reward": 20.520471018737357, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T12:43:16.961087"}
|