Initial commit
Browse files- dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/data +10 -10
- results.json +1 -1
dqn-SpaceInvadersNoFrameskip-v4.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 sha256:16c23aefc5bb8cf10e27be870a00e8890504e755182bd29fc9a869c9df4b4de5
|
3 |
+
size 27222221
|
dqn-SpaceInvadersNoFrameskip-v4/data
CHANGED
@@ -4,9 +4,9 @@
|
|
4 |
":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCUNublBvbGljeZSTlC4=",
|
5 |
"__module__": "stable_baselines3.dqn.policies",
|
6 |
"__doc__": "\n Policy class for DQN when using images as input.\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 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 CnnPolicy.__init__ at
|
8 |
"__abstractmethods__": "frozenset()",
|
9 |
-
"_abc_impl": "<_abc_data object at
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {},
|
@@ -42,12 +42,12 @@
|
|
42 |
"start_time": 1655799329.013306,
|
43 |
"learning_rate": {
|
44 |
":type:": "<class 'function'>",
|
45 |
-
":serialized:": "
|
46 |
},
|
47 |
"tensorboard_log": null,
|
48 |
"lr_schedule": {
|
49 |
":type:": "<class 'function'>",
|
50 |
-
":serialized:": "
|
51 |
},
|
52 |
"_last_obs": null,
|
53 |
"_last_episode_starts": {
|
@@ -83,12 +83,12 @@
|
|
83 |
":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
84 |
"__module__": "stable_baselines3.common.buffers",
|
85 |
"__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:\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 :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 ",
|
86 |
-
"__init__": "<function ReplayBuffer.__init__ at
|
87 |
-
"add": "<function ReplayBuffer.add at
|
88 |
-
"sample": "<function ReplayBuffer.sample at
|
89 |
-
"_get_samples": "<function ReplayBuffer._get_samples at
|
90 |
"__abstractmethods__": "frozenset()",
|
91 |
-
"_abc_impl": "<_abc_data object at
|
92 |
},
|
93 |
"replay_buffer_kwargs": {},
|
94 |
"train_freq": {
|
@@ -106,6 +106,6 @@
|
|
106 |
"exploration_rate": 0.01,
|
107 |
"exploration_schedule": {
|
108 |
":type:": "<class 'function'>",
|
109 |
-
":serialized:": "
|
110 |
}
|
111 |
}
|
|
|
4 |
":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCUNublBvbGljeZSTlC4=",
|
5 |
"__module__": "stable_baselines3.dqn.policies",
|
6 |
"__doc__": "\n Policy class for DQN when using images as input.\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 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 CnnPolicy.__init__ at 0x7f15301d90e0>",
|
8 |
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc_data object at 0x7f1530247750>"
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {},
|
|
|
42 |
"start_time": 1655799329.013306,
|
43 |
"learning_rate": {
|
44 |
":type:": "<class 'function'>",
|
45 |
+
":serialized:": "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"
|
46 |
},
|
47 |
"tensorboard_log": null,
|
48 |
"lr_schedule": {
|
49 |
":type:": "<class 'function'>",
|
50 |
+
":serialized:": "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"
|
51 |
},
|
52 |
"_last_obs": null,
|
53 |
"_last_episode_starts": {
|
|
|
83 |
":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
84 |
"__module__": "stable_baselines3.common.buffers",
|
85 |
"__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:\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 :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 ",
|
86 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7f15306d4a70>",
|
87 |
+
"add": "<function ReplayBuffer.add at 0x7f15306d4b00>",
|
88 |
+
"sample": "<function ReplayBuffer.sample at 0x7f153022fb00>",
|
89 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f153022fb90>",
|
90 |
"__abstractmethods__": "frozenset()",
|
91 |
+
"_abc_impl": "<_abc_data object at 0x7f1530710e70>"
|
92 |
},
|
93 |
"replay_buffer_kwargs": {},
|
94 |
"train_freq": {
|
|
|
106 |
"exploration_rate": 0.01,
|
107 |
"exploration_schedule": {
|
108 |
":type:": "<class 'function'>",
|
109 |
+
":serialized:": "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"
|
110 |
}
|
111 |
}
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": 529.0, "std_reward": 192.66291807195282, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-
|
|
|
1 |
+
{"mean_reward": 529.0, "std_reward": 192.66291807195282, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-24T12:40:18.141022"}
|