Initial commit
Browse files- README.md +1 -1
- args.yml +3 -1
- dqn-LunarLander-v2.zip +2 -2
- dqn-LunarLander-v2/_stable_baselines3_version +1 -1
- dqn-LunarLander-v2/data +22 -21
- dqn-LunarLander-v2/policy.optimizer.pth +1 -1
- dqn-LunarLander-v2/policy.pth +1 -1
- dqn-LunarLander-v2/system_info.txt +3 -3
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 173.57 +/- 138.27
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
args.yml
CHANGED
@@ -9,6 +9,8 @@
|
|
9 |
- LunarLander-v2
|
10 |
- - env_kwargs
|
11 |
- null
|
|
|
|
|
12 |
- - eval_episodes
|
13 |
- 5
|
14 |
- - eval_freq
|
@@ -54,7 +56,7 @@
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
|
|
9 |
- LunarLander-v2
|
10 |
- - env_kwargs
|
11 |
- null
|
12 |
+
- - eval_env_kwargs
|
13 |
+
- null
|
14 |
- - eval_episodes
|
15 |
- 5
|
16 |
- - eval_freq
|
|
|
56 |
- - save_replay_buffer
|
57 |
- false
|
58 |
- - seed
|
59 |
+
- 3661468958
|
60 |
- - storage
|
61 |
- null
|
62 |
- - study_name
|
dqn-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a98a18f0b5398cfdb758d719f02a2daf60391f94872cf53b88750b8bdfb7f765
|
3 |
+
size 1134391
|
dqn-LunarLander-v2/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
2.
|
|
|
1 |
+
2.3.2
|
dqn-LunarLander-v2/data
CHANGED
@@ -5,15 +5,15 @@
|
|
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
|
9 |
-
"_build": "<function DQNPolicy._build at
|
10 |
-
"make_q_net": "<function DQNPolicy.make_q_net at
|
11 |
-
"forward": "<function DQNPolicy.forward at
|
12 |
-
"_predict": "<function DQNPolicy._predict at
|
13 |
-
"_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at
|
14 |
-
"set_training_mode": "<function DQNPolicy.set_training_mode at
|
15 |
"__abstractmethods__": "frozenset()",
|
16 |
-
"_abc_impl": "<_abc._abc_data object at
|
17 |
},
|
18 |
"verbose": 1,
|
19 |
"policy_kwargs": {
|
@@ -27,10 +27,10 @@
|
|
27 |
"_num_timesteps_at_start": 0,
|
28 |
"seed": 0,
|
29 |
"action_noise": null,
|
30 |
-
"start_time":
|
31 |
"learning_rate": {
|
32 |
":type:": "<class 'function'>",
|
33 |
-
":serialized:": "
|
34 |
},
|
35 |
"tensorboard_log": null,
|
36 |
"_last_obs": null,
|
@@ -40,16 +40,16 @@
|
|
40 |
},
|
41 |
"_last_original_obs": {
|
42 |
":type:": "<class 'numpy.ndarray'>",
|
43 |
-
":serialized:": "
|
44 |
},
|
45 |
-
"_episode_num":
|
46 |
"use_sde": false,
|
47 |
"sde_sample_freq": -1,
|
48 |
"_current_progress_remaining": 0.0,
|
49 |
"_stats_window_size": 100,
|
50 |
"ep_info_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
-
":serialized:": "
|
53 |
},
|
54 |
"ep_success_buffer": {
|
55 |
":type:": "<class 'collections.deque'>",
|
@@ -92,14 +92,15 @@
|
|
92 |
":type:": "<class 'abc.ABCMeta'>",
|
93 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
94 |
"__module__": "stable_baselines3.common.buffers",
|
|
|
95 |
"__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 ",
|
96 |
-
"__init__": "<function ReplayBuffer.__init__ at
|
97 |
-
"add": "<function ReplayBuffer.add at
|
98 |
-
"sample": "<function ReplayBuffer.sample at
|
99 |
-
"_get_samples": "<function ReplayBuffer._get_samples at
|
100 |
-
"_maybe_cast_dtype": "<staticmethod object at
|
101 |
"__abstractmethods__": "frozenset()",
|
102 |
-
"_abc_impl": "<_abc._abc_data object at
|
103 |
},
|
104 |
"replay_buffer_kwargs": {},
|
105 |
"train_freq": {
|
@@ -116,12 +117,12 @@
|
|
116 |
"exploration_rate": 0.1,
|
117 |
"lr_schedule": {
|
118 |
":type:": "<class 'function'>",
|
119 |
-
":serialized:": "
|
120 |
},
|
121 |
"batch_norm_stats": [],
|
122 |
"batch_norm_stats_target": [],
|
123 |
"exploration_schedule": {
|
124 |
":type:": "<class 'function'>",
|
125 |
-
":serialized:": "
|
126 |
}
|
127 |
}
|
|
|
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 0x7f6f0281a8b0>",
|
9 |
+
"_build": "<function DQNPolicy._build at 0x7f6f0281a940>",
|
10 |
+
"make_q_net": "<function DQNPolicy.make_q_net at 0x7f6f0281a9d0>",
|
11 |
+
"forward": "<function DQNPolicy.forward at 0x7f6f0281aa60>",
|
12 |
+
"_predict": "<function DQNPolicy._predict at 0x7f6f0281aaf0>",
|
13 |
+
"_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f6f0281ab80>",
|
14 |
+
"set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f6f0281ac10>",
|
15 |
"__abstractmethods__": "frozenset()",
|
16 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f6f0281da40>"
|
17 |
},
|
18 |
"verbose": 1,
|
19 |
"policy_kwargs": {
|
|
|
27 |
"_num_timesteps_at_start": 0,
|
28 |
"seed": 0,
|
29 |
"action_noise": null,
|
30 |
+
"start_time": 1721099501012247454,
|
31 |
"learning_rate": {
|
32 |
":type:": "<class 'function'>",
|
33 |
+
":serialized:": "gAWV5AIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZy9ob21lL25zYW5naGkvc2FuZGJveC9hcHJlc3MvZHJsLTJlZC92ZW52L2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuFQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGcvaG9tZS9uc2FuZ2hpL3NhbmRib3gvYXByZXNzL2RybC0yZWQvdmVudi9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RKTSsr/bTYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
34 |
},
|
35 |
"tensorboard_log": null,
|
36 |
"_last_obs": null,
|
|
|
40 |
},
|
41 |
"_last_original_obs": {
|
42 |
":type:": "<class 'numpy.ndarray'>",
|
43 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZWYLvvAbM/ZckBvjVMV74faxM88ELJPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
44 |
},
|
45 |
+
"_episode_num": 238,
|
46 |
"use_sde": false,
|
47 |
"sde_sample_freq": -1,
|
48 |
"_current_progress_remaining": 0.0,
|
49 |
"_stats_window_size": 100,
|
50 |
"ep_info_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "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"
|
53 |
},
|
54 |
"ep_success_buffer": {
|
55 |
":type:": "<class 'collections.deque'>",
|
|
|
92 |
":type:": "<class 'abc.ABCMeta'>",
|
93 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
94 |
"__module__": "stable_baselines3.common.buffers",
|
95 |
+
"__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
|
96 |
"__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 ",
|
97 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7f6f029320d0>",
|
98 |
+
"add": "<function ReplayBuffer.add at 0x7f6f02932160>",
|
99 |
+
"sample": "<function ReplayBuffer.sample at 0x7f6f029321f0>",
|
100 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f6f02932280>",
|
101 |
+
"_maybe_cast_dtype": "<staticmethod object at 0x7f6f029b50a0>",
|
102 |
"__abstractmethods__": "frozenset()",
|
103 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f6f02985400>"
|
104 |
},
|
105 |
"replay_buffer_kwargs": {},
|
106 |
"train_freq": {
|
|
|
117 |
"exploration_rate": 0.1,
|
118 |
"lr_schedule": {
|
119 |
":type:": "<class 'function'>",
|
120 |
+
":serialized:": "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"
|
121 |
},
|
122 |
"batch_norm_stats": [],
|
123 |
"batch_norm_stats_target": [],
|
124 |
"exploration_schedule": {
|
125 |
":type:": "<class 'function'>",
|
126 |
+
":serialized:": "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"
|
127 |
}
|
128 |
}
|
dqn-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 558240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62e0e61e37ceeab6bf16f793473ac5acd19b81f7e1c008e01d3d308a55dfc57c
|
3 |
size 558240
|
dqn-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dac0ec8a66ea4170aac5a525b23f7be8e8ac33bffbd30fed11d059cd6d06a115
|
3 |
size 557362
|
dqn-LunarLander-v2/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
- OS: Linux-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024
|
2 |
- Python: 3.9.18
|
3 |
-
- Stable-Baselines3: 2.
|
4 |
-
- PyTorch: 2.1
|
5 |
- GPU Enabled: False
|
6 |
-
- Numpy: 1.26.
|
7 |
- Cloudpickle: 3.0.0
|
8 |
- Gymnasium: 0.29.1
|
9 |
- OpenAI Gym: 0.26.2
|
|
|
1 |
- OS: Linux-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024
|
2 |
- Python: 3.9.18
|
3 |
+
- Stable-Baselines3: 2.3.2
|
4 |
+
- PyTorch: 2.3.1+cpu
|
5 |
- GPU Enabled: False
|
6 |
+
- Numpy: 1.26.4
|
7 |
- Cloudpickle: 3.0.0
|
8 |
- Gymnasium: 0.29.1
|
9 |
- OpenAI Gym: 0.26.2
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87f609275f59c1d57847e72f74b6bf9077a4d7fd4e6df4e1afc6b86503360375
|
3 |
+
size 175744
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 173.57058009999997, "std_reward": 138.26935340666122, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T08:55:18.495887"}
|
train_eval_metrics.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:302689d10df00128d46eaafab9af4f4838885cb067ed695f57f9629fe0073754
|
3 |
+
size 7642
|