Upload
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: 230.29 +/- 34.06
|
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 0x7963cea79d80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7963cea79e10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7963cea79ea0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7963cea79f30>", "_build": "<function ActorCriticPolicy._build at 0x7963cea79fc0>", "forward": "<function ActorCriticPolicy.forward at 0x7963cea7a050>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7963cea7a0e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7963cea7a170>", "_predict": "<function ActorCriticPolicy._predict at 0x7963cea7a200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7963cea7a290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7963cea7a320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7963cea7a3b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7963cea73480>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689668408386567344, "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": 310, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.31 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "False", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "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 sha256:6e119dc226022e50a23c1ad226fcffab72725ba1d4db15923fda27a54da7116c
|
3 |
+
size 146162
|
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 0x7963cea79d80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7963cea79e10>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7963cea79ea0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7963cea79f30>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7963cea79fc0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7963cea7a050>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7963cea7a0e0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7963cea7a170>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7963cea7a200>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7963cea7a290>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7963cea7a320>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7963cea7a3b0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7963cea73480>"
|
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": 1689668408386567344,
|
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": 310,
|
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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
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 |
+
"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:d3b2efac858a756d88f8961d69207d2703334500af74d078e92955b16e96f14c
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad024f3e9c3cedef7618964590bb2250c6bc48eac6653f6bf33250d17cba6a29
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.31 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (140 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 230.29183730000005, "std_reward": 34.05886208963518, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-18T08:51:19.080768"}
|