Push to Hub
Browse files- README.md +37 -0
- config.json +1 -0
- dqn-LunarLander-v2.zip +3 -0
- dqn-LunarLander-v2/_stable_baselines3_version +1 -0
- dqn-LunarLander-v2/data +121 -0
- dqn-LunarLander-v2/policy.optimizer.pth +3 -0
- dqn-LunarLander-v2/policy.pth +3 -0
- dqn-LunarLander-v2/pytorch_variables.pth +3 -0
- dqn-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: DQN
|
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: 40.65 +/- 103.04
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **DQN** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **DQN** 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:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=", "__module__": "stable_baselines3.dqn.policies", "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}", "__doc__": "\n Policy class with Q-Value Net and target net for DQN\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 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 DQNPolicy.__init__ at 0x7fcbcc9b4ca0>", "_build": "<function DQNPolicy._build at 0x7fcbcc9b4d30>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7fcbcc9b4dc0>", "forward": "<function DQNPolicy.forward at 0x7fcbcc9b4e50>", "_predict": "<function DQNPolicy._predict at 0x7fcbcc9b4ee0>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fcbcc9b4f70>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fcbcc9b5000>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fcbcc9b1440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688626326065901139, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABq94D0ZRRk/UGUPvVS3pr1NVIm8U0ZRuwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAIB14T0jvRk/MhM7vZAEqb14BYi8YLVSvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_episode_num": 620, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 12500, "buffer_size": 1000000, "batch_size": 32, "learning_starts": 50000, "tau": 1.0, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ", "__init__": "<function ReplayBuffer.__init__ at 0x7fcbcc985120>", "add": "<function ReplayBuffer.add at 0x7fcbcc9851b0>", "sample": "<function ReplayBuffer.sample at 0x7fcbcc985240>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7fcbcc9852d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fcbcc97f080>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.1, "exploration_fraction": 0.1, "target_update_interval": 250, "_n_calls": 100000, "max_grad_norm": 10, "exploration_rate": 0.1, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
dqn-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3aa1b4684af617ceecef8db875a5cb9480b9d0ae98c5895ea65d4cab48607cb
|
3 |
+
size 105414
|
dqn-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0
|
dqn-LunarLander-v2/data
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
|
5 |
+
"__module__": "stable_baselines3.dqn.policies",
|
6 |
+
"__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}",
|
7 |
+
"__doc__": "\n Policy class with Q-Value Net and target net for DQN\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 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 ",
|
8 |
+
"__init__": "<function DQNPolicy.__init__ at 0x7fcbcc9b4ca0>",
|
9 |
+
"_build": "<function DQNPolicy._build at 0x7fcbcc9b4d30>",
|
10 |
+
"make_q_net": "<function DQNPolicy.make_q_net at 0x7fcbcc9b4dc0>",
|
11 |
+
"forward": "<function DQNPolicy.forward at 0x7fcbcc9b4e50>",
|
12 |
+
"_predict": "<function DQNPolicy._predict at 0x7fcbcc9b4ee0>",
|
13 |
+
"_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fcbcc9b4f70>",
|
14 |
+
"set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fcbcc9b5000>",
|
15 |
+
"__abstractmethods__": "frozenset()",
|
16 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fcbcc9b1440>"
|
17 |
+
},
|
18 |
+
"verbose": 1,
|
19 |
+
"policy_kwargs": {},
|
20 |
+
"num_timesteps": 100000,
|
21 |
+
"_total_timesteps": 100000,
|
22 |
+
"_num_timesteps_at_start": 0,
|
23 |
+
"seed": null,
|
24 |
+
"action_noise": null,
|
25 |
+
"start_time": 1688626326065901139,
|
26 |
+
"learning_rate": 0.0001,
|
27 |
+
"tensorboard_log": null,
|
28 |
+
"_last_obs": {
|
29 |
+
":type:": "<class 'numpy.ndarray'>",
|
30 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABq94D0ZRRk/UGUPvVS3pr1NVIm8U0ZRuwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
31 |
+
},
|
32 |
+
"_last_episode_starts": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
35 |
+
},
|
36 |
+
"_last_original_obs": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAIB14T0jvRk/MhM7vZAEqb14BYi8YLVSvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_episode_num": 620,
|
41 |
+
"use_sde": false,
|
42 |
+
"sde_sample_freq": -1,
|
43 |
+
"_current_progress_remaining": 0.0,
|
44 |
+
"_stats_window_size": 100,
|
45 |
+
"ep_info_buffer": {
|
46 |
+
":type:": "<class 'collections.deque'>",
|
47 |
+
":serialized:": "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"
|
48 |
+
},
|
49 |
+
"ep_success_buffer": {
|
50 |
+
":type:": "<class 'collections.deque'>",
|
51 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
52 |
+
},
|
53 |
+
"_n_updates": 12500,
|
54 |
+
"buffer_size": 1000000,
|
55 |
+
"batch_size": 32,
|
56 |
+
"learning_starts": 50000,
|
57 |
+
"tau": 1.0,
|
58 |
+
"gamma": 0.99,
|
59 |
+
"gradient_steps": 1,
|
60 |
+
"optimize_memory_usage": false,
|
61 |
+
"replay_buffer_class": {
|
62 |
+
":type:": "<class 'abc.ABCMeta'>",
|
63 |
+
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
64 |
+
"__module__": "stable_baselines3.common.buffers",
|
65 |
+
"__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
66 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7fcbcc985120>",
|
67 |
+
"add": "<function ReplayBuffer.add at 0x7fcbcc9851b0>",
|
68 |
+
"sample": "<function ReplayBuffer.sample at 0x7fcbcc985240>",
|
69 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7fcbcc9852d0>",
|
70 |
+
"__abstractmethods__": "frozenset()",
|
71 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fcbcc97f080>"
|
72 |
+
},
|
73 |
+
"replay_buffer_kwargs": {},
|
74 |
+
"train_freq": {
|
75 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
76 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
77 |
+
},
|
78 |
+
"use_sde_at_warmup": false,
|
79 |
+
"exploration_initial_eps": 1.0,
|
80 |
+
"exploration_final_eps": 0.1,
|
81 |
+
"exploration_fraction": 0.1,
|
82 |
+
"target_update_interval": 250,
|
83 |
+
"_n_calls": 100000,
|
84 |
+
"max_grad_norm": 10,
|
85 |
+
"exploration_rate": 0.1,
|
86 |
+
"observation_space": {
|
87 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
88 |
+
":serialized:": "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",
|
89 |
+
"dtype": "float32",
|
90 |
+
"bounded_below": "[ True True True True True True True True]",
|
91 |
+
"bounded_above": "[ True True True True True True True True]",
|
92 |
+
"_shape": [
|
93 |
+
8
|
94 |
+
],
|
95 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
96 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
97 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
98 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
99 |
+
"_np_random": null
|
100 |
+
},
|
101 |
+
"action_space": {
|
102 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
103 |
+
":serialized:": "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",
|
104 |
+
"n": "4",
|
105 |
+
"start": "0",
|
106 |
+
"_shape": [],
|
107 |
+
"dtype": "int64",
|
108 |
+
"_np_random": "Generator(PCG64)"
|
109 |
+
},
|
110 |
+
"n_envs": 1,
|
111 |
+
"lr_schedule": {
|
112 |
+
":type:": "<class 'function'>",
|
113 |
+
":serialized:": "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"
|
114 |
+
},
|
115 |
+
"batch_norm_stats": [],
|
116 |
+
"batch_norm_stats_target": [],
|
117 |
+
"exploration_schedule": {
|
118 |
+
":type:": "<class 'function'>",
|
119 |
+
":serialized:": "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"
|
120 |
+
}
|
121 |
+
}
|
dqn-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad82fe01b3280a928433b3ae9573fd3bc3f39db61d324c538664d97eb615460d
|
3 |
+
size 44975
|
dqn-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e398f1c9957ba7ab716ab5504d0dac33b88c9db29e25277b133410a57c115b69
|
3 |
+
size 44033
|
dqn-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
|
dqn-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: True
|
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 (190 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 40.64543064303723, "std_reward": 103.04227033241897, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-06T07:22:07.368226"}
|