justdimaa commited on
Commit
fd4b456
1 Parent(s): 0c8d897

Initial commit

Browse files
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d416dfbdeeff0bbc5452b5af9e239b2fd05fac3537a4e89cb6f62e6cf4b76403
3
  size 27220466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb1bc35ab588c71ac9608b4048a8461aed389c856bfa532fab7f17a2639de72
3
  size 27220466
dqn-SpaceInvadersNoFrameskip-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 0x7f768e79d300>",
8
  "__abstractmethods__": "frozenset()",
9
- "_abc_impl": "<_abc._abc_data object at 0x7f768e78f240>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {},
@@ -84,13 +84,13 @@
84
  "__module__": "stable_baselines3.common.buffers",
85
  "__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'>}",
86
  "__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 ",
87
- "__init__": "<function ReplayBuffer.__init__ at 0x7f768ef64900>",
88
- "add": "<function ReplayBuffer.add at 0x7f768ef64a40>",
89
- "sample": "<function ReplayBuffer.sample at 0x7f768ef64ae0>",
90
- "_get_samples": "<function ReplayBuffer._get_samples at 0x7f768ef64b80>",
91
- "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f768ef64c20>)>",
92
  "__abstractmethods__": "frozenset()",
93
- "_abc_impl": "<_abc._abc_data object at 0x7f768f0c7480>"
94
  },
95
  "replay_buffer_kwargs": {},
96
  "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 0x7fd11e5a99e0>",
8
  "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7fd11e5b0600>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {},
 
84
  "__module__": "stable_baselines3.common.buffers",
85
  "__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'>}",
86
  "__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 ",
87
+ "__init__": "<function ReplayBuffer.__init__ at 0x7fd11ed70fe0>",
88
+ "add": "<function ReplayBuffer.add at 0x7fd11ed71120>",
89
+ "sample": "<function ReplayBuffer.sample at 0x7fd11ed711c0>",
90
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7fd11ed71260>",
91
+ "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fd11ed71300>)>",
92
  "__abstractmethods__": "frozenset()",
93
+ "_abc_impl": "<_abc._abc_data object at 0x7fd163edbc80>"
94
  },
95
  "replay_buffer_kwargs": {},
96
  "train_freq": {
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0927ece387922e508bada92ae452b4fa88436a1854937c337a2ad5f81e2bb8e5
3
+ size 200360
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 687.0, "std_reward": 185.42114226808118, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-02T20:15:16.111930"}
 
1
+ {"mean_reward": 687.0, "std_reward": 185.42114226808118, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-02T20:16:43.478524"}