Quentin Gallouédec commited on
Commit
fcadaa9
1 Parent(s): c4e9995

Stochastic eval

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: MiniGrid-Unlock-v0
17
  metrics:
18
  - type: mean_reward
19
- value: 0.77 +/- 0.38
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: MiniGrid-Unlock-v0
17
  metrics:
18
  - type: mean_reward
19
+ value: 0.95 +/- 0.02
20
  name: mean_reward
21
  verified: false
22
  ---
ppo-MiniGrid-Unlock-v0.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c054597493091746bf301c002409f205bb090bb08880f3ba540395a1594c67e3
3
  size 4390837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdc2b0695415488ce94a7bf47b8bcdfdd40aaec562f74adfe63060a33efb64e
3
  size 4390837
ppo-MiniGrid-Unlock-v0/data CHANGED
@@ -4,20 +4,20 @@
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ActorCriticPolicy.__init__ at 0x7f20514d4040>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f20514d40d0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f20514d4160>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f20514d41f0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7f20514d4280>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7f20514d4310>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f20514d43a0>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f20514d4430>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7f20514d44c0>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f20514d4550>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f20514d45e0>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f20514d4670>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7f2051a7dcc0>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
 
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ActorCriticPolicy.__init__ at 0x7f8b0a754040>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8b0a7540d0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8b0a754160>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8b0a7541f0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f8b0a754280>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f8b0a754310>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8b0a7543a0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8b0a754430>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f8b0a7544c0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8b0a754550>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8b0a7545e0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8b0a754670>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f8b0a752b40>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38cf7d8e394d0be430890bb88911a693f352a4277499c244e1d2a2d9075f6204
3
- size 121485
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb7702a3081c603a5e549bb6b0ed49d99084e588a2be6cd5e4801ff1600f06f
3
+ size 231699
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 0.7671875000000001, "std_reward": 0.38382391898011, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-31T18:23:50.325074"}
 
1
+ {"mean_reward": 0.9540625, "std_reward": 0.017004709825515992, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-31T20:13:50.153237"}