Push to Hub
Browse files- DQN-CartPole-v1.zip +2 -2
- DQN-CartPole-v1/_stable_baselines3_version +1 -1
- DQN-CartPole-v1/data +23 -24
- DQN-CartPole-v1/policy.optimizer.pth +2 -2
- DQN-CartPole-v1/policy.pth +2 -2
- DQN-CartPole-v1/pytorch_variables.pth +2 -2
- DQN-CartPole-v1/system_info.txt +7 -7
- README.md +1 -1
- config.json +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
DQN-CartPole-v1.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 sha256:10bfe3c0339c93755c5bc50a90bcd268cd8ed492d0bc3de794e297a8a72afb97
|
3 |
+
size 1106794
|
DQN-CartPole-v1/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
2.
|
|
|
1 |
+
2.1.0
|
DQN-CartPole-v1/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": {
|
@@ -30,12 +30,12 @@
|
|
30 |
"_num_timesteps_at_start": 0,
|
31 |
"seed": null,
|
32 |
"action_noise": null,
|
33 |
-
"start_time":
|
34 |
"learning_rate": 0.0001,
|
35 |
"tensorboard_log": null,
|
36 |
"_last_obs": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_episode_starts": {
|
41 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -43,16 +43,16 @@
|
|
43 |
},
|
44 |
"_last_original_obs": {
|
45 |
":type:": "<class 'numpy.ndarray'>",
|
46 |
-
":serialized:": "
|
47 |
},
|
48 |
-
"_episode_num":
|
49 |
"use_sde": false,
|
50 |
"sde_sample_freq": -1,
|
51 |
"_current_progress_remaining": 0.0,
|
52 |
"_stats_window_size": 100,
|
53 |
"ep_info_buffer": {
|
54 |
":type:": "<class 'collections.deque'>",
|
55 |
-
":serialized:": "
|
56 |
},
|
57 |
"ep_success_buffer": {
|
58 |
":type:": "<class 'collections.deque'>",
|
@@ -61,7 +61,7 @@
|
|
61 |
"_n_updates": 12500,
|
62 |
"observation_space": {
|
63 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
64 |
-
":serialized:": "
|
65 |
"dtype": "float32",
|
66 |
"bounded_below": "[ True True True True]",
|
67 |
"bounded_above": "[ True True True True]",
|
@@ -76,7 +76,7 @@
|
|
76 |
},
|
77 |
"action_space": {
|
78 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
79 |
-
":serialized:": "
|
80 |
"n": "2",
|
81 |
"start": "0",
|
82 |
"_shape": [],
|
@@ -95,15 +95,14 @@
|
|
95 |
":type:": "<class 'abc.ABCMeta'>",
|
96 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
97 |
"__module__": "stable_baselines3.common.buffers",
|
98 |
-
"__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'>}",
|
99 |
"__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 ",
|
100 |
-
"__init__": "<function ReplayBuffer.__init__ at
|
101 |
-
"add": "<function ReplayBuffer.add at
|
102 |
-
"sample": "<function ReplayBuffer.sample at
|
103 |
-
"_get_samples": "<function ReplayBuffer._get_samples at
|
104 |
-
"_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at
|
105 |
"__abstractmethods__": "frozenset()",
|
106 |
-
"_abc_impl": "<_abc._abc_data object at
|
107 |
},
|
108 |
"replay_buffer_kwargs": {},
|
109 |
"train_freq": {
|
@@ -120,12 +119,12 @@
|
|
120 |
"exploration_rate": 0.05,
|
121 |
"lr_schedule": {
|
122 |
":type:": "<class 'function'>",
|
123 |
-
":serialized:": "
|
124 |
},
|
125 |
"batch_norm_stats": [],
|
126 |
"batch_norm_stats_target": [],
|
127 |
"exploration_schedule": {
|
128 |
":type:": "<class 'function'>",
|
129 |
-
":serialized:": "
|
130 |
}
|
131 |
}
|
|
|
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 0x7f6007daf0a0>",
|
9 |
+
"_build": "<function DQNPolicy._build at 0x7f6007daf130>",
|
10 |
+
"make_q_net": "<function DQNPolicy.make_q_net at 0x7f6007daf1c0>",
|
11 |
+
"forward": "<function DQNPolicy.forward at 0x7f6007daf250>",
|
12 |
+
"_predict": "<function DQNPolicy._predict at 0x7f6007daf2e0>",
|
13 |
+
"_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f6007daf370>",
|
14 |
+
"set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f6007daf400>",
|
15 |
"__abstractmethods__": "frozenset()",
|
16 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f600b812540>"
|
17 |
},
|
18 |
"verbose": 1,
|
19 |
"policy_kwargs": {
|
|
|
30 |
"_num_timesteps_at_start": 0,
|
31 |
"seed": null,
|
32 |
"action_noise": null,
|
33 |
+
"start_time": 1699149162696540850,
|
34 |
"learning_rate": 0.0001,
|
35 |
"tensorboard_log": null,
|
36 |
"_last_obs": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAA1sKbwZu2k7nqy0vGI2cz2UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
|
39 |
},
|
40 |
"_last_episode_starts": {
|
41 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
43 |
},
|
44 |
"_last_original_obs": {
|
45 |
":type:": "<class 'numpy.ndarray'>",
|
46 |
+
":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOZxarxIMks+xlyPvAYzab6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
|
47 |
},
|
48 |
+
"_episode_num": 4059,
|
49 |
"use_sde": false,
|
50 |
"sde_sample_freq": -1,
|
51 |
"_current_progress_remaining": 0.0,
|
52 |
"_stats_window_size": 100,
|
53 |
"ep_info_buffer": {
|
54 |
":type:": "<class 'collections.deque'>",
|
55 |
+
":serialized:": "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"
|
56 |
},
|
57 |
"ep_success_buffer": {
|
58 |
":type:": "<class 'collections.deque'>",
|
|
|
61 |
"_n_updates": 12500,
|
62 |
"observation_space": {
|
63 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
64 |
+
":serialized:": "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",
|
65 |
"dtype": "float32",
|
66 |
"bounded_below": "[ True True True True]",
|
67 |
"bounded_above": "[ True True True True]",
|
|
|
76 |
},
|
77 |
"action_space": {
|
78 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
79 |
+
":serialized:": "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",
|
80 |
"n": "2",
|
81 |
"start": "0",
|
82 |
"_shape": [],
|
|
|
95 |
":type:": "<class 'abc.ABCMeta'>",
|
96 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
97 |
"__module__": "stable_baselines3.common.buffers",
|
|
|
98 |
"__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 ",
|
99 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7f6007d9f760>",
|
100 |
+
"add": "<function ReplayBuffer.add at 0x7f6007d9f7f0>",
|
101 |
+
"sample": "<function ReplayBuffer.sample at 0x7f6007d9f880>",
|
102 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f6007d9f910>",
|
103 |
+
"_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f6007d9f9a0>)>",
|
104 |
"__abstractmethods__": "frozenset()",
|
105 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f6007da0e40>"
|
106 |
},
|
107 |
"replay_buffer_kwargs": {},
|
108 |
"train_freq": {
|
|
|
119 |
"exploration_rate": 0.05,
|
120 |
"lr_schedule": {
|
121 |
":type:": "<class 'function'>",
|
122 |
+
":serialized:": "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"
|
123 |
},
|
124 |
"batch_norm_stats": [],
|
125 |
"batch_norm_stats_target": [],
|
126 |
"exploration_schedule": {
|
127 |
":type:": "<class 'function'>",
|
128 |
+
":serialized:": "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"
|
129 |
}
|
130 |
}
|
DQN-CartPole-v1/policy.optimizer.pth
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:a7492ebcd8f278c6cb49b36cbcb598d1a4c5e333e342b2e27cbeaf9bc330fd4f
|
3 |
+
size 545519
|
DQN-CartPole-v1/policy.pth
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 sha256:5097ef26ecfc88e60f922b08a0f30f69d4f7a0e40ae43e4fb0251c411909eec8
|
3 |
+
size 544641
|
DQN-CartPole-v1/pytorch_variables.pth
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:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
DQN-CartPole-v1/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
-
- OS: Linux-5.15.
|
2 |
-
- Python: 3.10.
|
3 |
-
- Stable-Baselines3: 2.
|
4 |
-
- PyTorch: 2.1
|
5 |
-
- GPU Enabled:
|
6 |
-
- Numpy: 1.
|
7 |
- Cloudpickle: 2.2.1
|
8 |
-
- Gymnasium: 0.
|
9 |
- OpenAI Gym: 0.26.2
|
|
|
1 |
+
- OS: Linux-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Jan 27 02:56:13 UTC 2023
|
2 |
+
- Python: 3.10.6
|
3 |
+
- Stable-Baselines3: 2.1.0
|
4 |
+
- PyTorch: 2.0.1+cu117
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.25.1
|
7 |
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.26.2
|
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: CartPole-v1
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: CartPole-v1
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 194.70 +/- 32.22
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 0x791a617ede10>", "_build": "<function DQNPolicy._build at 0x791a617edea0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x791a617edf30>", "forward": "<function DQNPolicy.forward at 0x791a617edfc0>", "_predict": "<function DQNPolicy._predict at 0x791a617ee050>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x791a617ee0e0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x791a617ee170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x791a617ebe40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": [256, 256]}, "num_timesteps": 100000, "_total_timesteps": 100000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698322213186748147, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAHzTiT4Vyxs+mtQCvdzqRz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAFJGhj4wkrE+lUf3vE7Es72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 3595, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "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", "__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'>}", "__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 0x791a617c6200>", "add": "<function ReplayBuffer.add at 0x791a617c6290>", "sample": "<function ReplayBuffer.sample at 0x791a617c6320>", "_get_samples": "<function ReplayBuffer._get_samples at 0x791a617c63b0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x791a617c6440>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x791a617cd9c0>"}, "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": 0.05, "exploration_fraction": 0.1, "target_update_interval": 10000, "_n_calls": 100000, "max_grad_norm": 10, "exploration_rate": 0.05, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.0a8", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}
|
|
|
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 0x7f6007daf0a0>", "_build": "<function DQNPolicy._build at 0x7f6007daf130>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7f6007daf1c0>", "forward": "<function DQNPolicy.forward at 0x7f6007daf250>", "_predict": "<function DQNPolicy._predict at 0x7f6007daf2e0>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f6007daf370>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f6007daf400>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f600b812540>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": [256, 256]}, "num_timesteps": 100000, "_total_timesteps": 100000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1699149162696540850, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAA1sKbwZu2k7nqy0vGI2cz2UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOZxarxIMks+xlyPvAYzab6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 4059, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "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 0x7f6007d9f760>", "add": "<function ReplayBuffer.add at 0x7f6007d9f7f0>", "sample": "<function ReplayBuffer.sample at 0x7f6007d9f880>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7f6007d9f910>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f6007d9f9a0>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6007da0e40>"}, "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": 0.05, "exploration_fraction": 0.1, "target_update_interval": 10000, "_n_calls": 100000, "max_grad_norm": 10, "exploration_rate": 0.05, "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-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Jan 27 02:56:13 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "False", "Numpy": "1.25.1", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 194.7, "std_reward": 32.21505859066533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-05T07:25:32.966629"}
|