reinforced-kathi
commited on
Commit
•
8197cc4
1
Parent(s):
c5fa0f9
First commit for lunar lander
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 +99 -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 +9 -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: 272.15 +/- 18.48
|
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 0x7c024a7fc820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c024a7fc8b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c024a7fc940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c024a7fc9d0>", "_build": "<function ActorCriticPolicy._build at 0x7c024a7fca60>", "forward": "<function ActorCriticPolicy.forward at 0x7c024a7fcaf0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c024a7fcb80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c024a7fcc10>", "_predict": "<function ActorCriticPolicy._predict at 0x7c024a7fcca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c024a7fcd30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c024a7fcdc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c024a7fce50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c024a798e40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1729328303175471378, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWVrQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFowEZnVuY5SMDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5928869cb32072b172297f7570dea886175c56f183ac25a017721954cc90632
|
3 |
+
size 147968
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7c024a7fc820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c024a7fc8b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c024a7fc940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c024a7fc9d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7c024a7fca60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7c024a7fcaf0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7c024a7fcb80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c024a7fcc10>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7c024a7fcca0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c024a7fcd30>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c024a7fcdc0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7c024a7fce50>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7c024a798e40>"
|
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": 1729328303175471378,
|
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'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
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,
|
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 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3acf9b0e2adb9a8f423123400aa74a9ceae0213408f8f723c49294d627cf6486
|
3 |
+
size 88362
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:302913e8d5d6fcc5f85f87c6f2d1c81e72484281369ec76ff94b7efeea356959
|
3 |
+
size 43762
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.4.1+cu121
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.26.4
|
7 |
+
- Cloudpickle: 3.1.0
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (182 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 272.15353159999995, "std_reward": 18.480050261124422, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-19T09:37:20.469972"}
|