MattStammers
commited on
Commit
•
3341618
1
Parent(s):
4bad67c
Initial commit
Browse files- dqn-QbertNoFrameskip-v4.zip +1 -1
- dqn-QbertNoFrameskip-v4/data +8 -8
- results.json +1 -1
dqn-QbertNoFrameskip-v4.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27217851
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0da26ef6b865d14af1073533060c2bb3d45276c9dafb5331a1e1eb93790e6f7f
|
3 |
size 27217851
|
dqn-QbertNoFrameskip-v4/data
CHANGED
@@ -4,9 +4,9 @@
|
|
4 |
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCUNublBvbGljeZSTlC4=",
|
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._abc_data object at
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {},
|
@@ -83,13 +83,13 @@
|
|
83 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
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: 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 ",
|
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 |
-
"_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at
|
91 |
"__abstractmethods__": "frozenset()",
|
92 |
-
"_abc_impl": "<_abc._abc_data object at
|
93 |
},
|
94 |
"replay_buffer_kwargs": {},
|
95 |
"train_freq": {
|
|
|
4 |
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCUNublBvbGljeZSTlC4=",
|
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 0x7a6776effbe0>",
|
8 |
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc._abc_data object at 0x7a6776d12580>"
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {},
|
|
|
83 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
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: 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 ",
|
86 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7a6776efbd00>",
|
87 |
+
"add": "<function ReplayBuffer.add at 0x7a6776efbd90>",
|
88 |
+
"sample": "<function ReplayBuffer.sample at 0x7a6776efbe20>",
|
89 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7a6776efbeb0>",
|
90 |
+
"_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7a6776efbf40>)>",
|
91 |
"__abstractmethods__": "frozenset()",
|
92 |
+
"_abc_impl": "<_abc._abc_data object at 0x7a6776e77ec0>"
|
93 |
},
|
94 |
"replay_buffer_kwargs": {},
|
95 |
"train_freq": {
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": 9365.0, "std_reward": 4858.693239956604, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-23T07:
|
|
|
1 |
+
{"mean_reward": 9365.0, "std_reward": 4858.693239956604, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-23T07:12:54.028746"}
|