Commit
•
db524f9
1
Parent(s):
2a6afd4
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +1 -1
- ppo-LunarLander-v2/data +15 -15
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -104.91 +/- 121.92
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 ActorCriticPolicy.__init__ at 0x000001EA403EFD30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001EA403EFDC0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001EA403EFE50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001EA403EFEE0>", "_build": "<function ActorCriticPolicy._build at 0x000001EA403EFF70>", "forward": "<function ActorCriticPolicy.forward at 0x000001EA403F2040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001EA403F20D0>", "_predict": "<function ActorCriticPolicy._predict at 0x000001EA403F2160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001EA403F21F0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001EA403F2280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001EA403F2310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001EA403F3200>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 65536, "_total_timesteps": 50000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1666237444036078900, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.3107200000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Windows-10-10.0.19044-SP0 10.0.19044", "Python": "3.9.7", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1", "GPU Enabled": "False", "Numpy": "1.23.3", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 ActorCriticPolicy.__init__ at 0x00000182B5591700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000182B5591790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x00000182B5591820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000182B55918B0>", "_build": "<function ActorCriticPolicy._build at 0x00000182B5591940>", "forward": "<function ActorCriticPolicy.forward at 0x00000182B55919D0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000182B5591A60>", "_predict": "<function ActorCriticPolicy._predict at 0x00000182B5591AF0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000182B5591B80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000182B5591C10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x00000182B5591CA0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x00000182B55981C0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 65536, "_total_timesteps": 50000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1666238912003782700, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.3107200000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Windows-10-10.0.19044-SP0 10.0.19044", "Python": "3.9.7", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1", "GPU Enabled": "False", "Numpy": "1.23.3", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 146401
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c802f9a3e0e3a8d9c03cf39ab8437b854e5da4bd3b5438cc1cb9d1eef37a0b0
|
3 |
size 146401
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,19 +4,19 @@
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc._abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -47,7 +47,7 @@
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -69,7 +69,7 @@
|
|
69 |
"_current_progress_remaining": -0.3107200000000001,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x00000182B5591700>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000182B5591790>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x00000182B5591820>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000182B55918B0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x00000182B5591940>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x00000182B55919D0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000182B5591A60>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x00000182B5591AF0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000182B5591B80>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000182B5591C10>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x00000182B5591CA0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x00000182B55981C0>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1666238912003782700,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
69 |
"_current_progress_remaining": -0.3107200000000001,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87545
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7c88ff771e5ad9aafd03ee8ed392998001356fc027e399626b0a8c439965ed1
|
3 |
size 87545
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43073
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cb3b49bfa634ae9f8450e78e70e90af87fc94fec8294245cba50f3d573cbef3
|
3 |
size 43073
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -104.9113875208368, "std_reward": 121.91572414084844, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-10-19T23:10:21.659099"}
|