Initial commit

README.md

@@ -79,3 +79,8 @@ OrderedDict([('batch_size', 32),
              ('train_freq', 4),
              ('normalize', False)])
 ```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e49e2498be8a2a066cb7021abcbd32d71eebb6f726c9b708acdddf37a6ede1
+oid sha256:897e8749e27c04e302e332bb04ba1f887a59245ede13e703320605ab9c896291
 size 27220166

dqn-SpaceInvadersNoFrameskip-v4/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCUNublBvbGljeZSTlC4=",
         "__module__": "stable_baselines3.dqn.policies",
         "__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    ",
-        "__init__": "<function CnnPolicy.__init__ at 0x7f735b1a36d0>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7f2c164f76d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f735b1c9b00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f2c165363c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -84,13 +84,13 @@
         "__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 0x7f735b4dfc70>",
-        "add": "<function ReplayBuffer.add at 0x7f735b4dfd00>",
-        "sample": "<function ReplayBuffer.sample at 0x7f735b4dfd90>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f735b4dfe20>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f735b4dfeb0>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f2c16857c70>",
+        "add": "<function ReplayBuffer.add at 0x7f2c16857d00>",
+        "sample": "<function ReplayBuffer.sample at 0x7f2c16857d90>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f2c16857e20>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f2c16857eb0>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f735b45b700>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f2c167cd700>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

env_kwargs.yml

@@ -1 +1 @@
-{}
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a749ce5a592e3fc70a380461934ba21d70a74e6bd7529c23510320c4fc7553
+size 256699

results.json

@@ -1 +1 @@
-{"mean_reward": 595.0, "std_reward": 112.49444430726346, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-22T21:30:44.210347"}
+{"mean_reward": 595.0, "std_reward": 112.49444430726346, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-22T22:18:52.461919"}