RL v2 LunarLander-v2 agent
Browse files- README.md +6 -5
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/_stable_baselines3_version +1 -1
- ppo-LunarLander-v2/data +26 -26
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +5 -5
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -8,16 +8,17 @@ tags:
|
|
8 |
model-index:
|
9 |
- name: PPO
|
10 |
results:
|
11 |
-
-
|
12 |
-
- type: mean_reward
|
13 |
-
value: 252.75 +/- 15.81
|
14 |
-
name: mean_reward
|
15 |
-
task:
|
16 |
type: reinforcement-learning
|
17 |
name: reinforcement-learning
|
18 |
dataset:
|
19 |
name: LunarLander-v2
|
20 |
type: LunarLander-v2
|
|
|
|
|
|
|
|
|
|
|
21 |
---
|
22 |
|
23 |
# **PPO** Agent playing **LunarLander-v2**
|
|
|
8 |
model-index:
|
9 |
- name: PPO
|
10 |
results:
|
11 |
+
- task:
|
|
|
|
|
|
|
|
|
12 |
type: reinforcement-learning
|
13 |
name: reinforcement-learning
|
14 |
dataset:
|
15 |
name: LunarLander-v2
|
16 |
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 273.91 +/- 12.60
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
---
|
23 |
|
24 |
# **PPO** Agent playing **LunarLander-v2**
|
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 0x7f8461498940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f84614989d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8461498a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8461498af0>", "_build": "<function ActorCriticPolicy._build at 0x7f8461498b80>", "forward": "<function ActorCriticPolicy.forward at 0x7f8461498c10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8461498ca0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8461498d30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8461498dc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8461498e50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8461498ee0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8461a49480>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1659665560.5138562, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVgBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIlkG1wQn+ZUCUhpRSlIwBbJRN6AOMAXSUR0CU9uCaJAMVdX2UKGgGaAloD0MIwcdgxam/ZUCUhpRSlGgVTegDaBZHQJT4gVN5+ph1fZQoaAZoCWgPQwiIu3oVGSpjQJSGlFKUaBVN6ANoFkdAlPj8ySFGonV9lChoBmgJaA9DCEBtVKeDjGNAlIaUUpRoFU3oA2gWR0CU+7rBj4HpdX2UKGgGaAloD0MIeeblsHseYkCUhpRSlGgVTegDaBZHQJT91LwnYxt1fZQoaAZoCWgPQwhBvK5fsPJmQJSGlFKUaBVN6ANoFkdAlP/rmITGpHV9lChoBmgJaA9DCIbGE0Ec5WBAlIaUUpRoFU3oA2gWR0CVAkCDEm6YdX2UKGgGaAloD0MIsd6oFaYQZ0CUhpRSlGgVTegDaBZHQJUIpomG/N91fZQoaAZoCWgPQwhJSnoYWuVFQJSGlFKUaBVL9WgWR0CVCcicG1QZdX2UKGgGaAloD0MIVIzzN6EPZECUhpRSlGgVTegDaBZHQJUM8LQXyiF1fZQoaAZoCWgPQwhkXdxGg1tjQJSGlFKUaBVN6ANoFkdAlRHyWNWEK3V9lChoBmgJaA9DCLCMDd1skG9AlIaUUpRoFU2WA2gWR0CVHFZHuqm1dX2UKGgGaAloD0MIHCPZI9TJZUCUhpRSlGgVTegDaBZHQJUidgfEGaB1fZQoaAZoCWgPQwh6Oey+41JkQJSGlFKUaBVN6ANoFkdAlUzFrdnCf3V9lChoBmgJaA9DCJGcTNwqTmVAlIaUUpRoFU3oA2gWR0CVTv4tYjjadX2UKGgGaAloD0MIjnbc8LuKYUCUhpRSlGgVTegDaBZHQJVPNOXVsk91fZQoaAZoCWgPQwg0nZ0MjrFjQJSGlFKUaBVN6ANoFkdAlVfOearmyXV9lChoBmgJaA9DCHeHFAOkbWJAlIaUUpRoFU3oA2gWR0CVWGtfoicHdX2UKGgGaAloD0MIQmDl0KLuYECUhpRSlGgVTegDaBZHQJVaDevZAY51fZQoaAZoCWgPQwjRzf5AuRNkQJSGlFKUaBVN6ANoFkdAlVqNB4Uvf3V9lChoBmgJaA9DCEG2LF+XrmZAlIaUUpRoFU3oA2gWR0CVX6K2rn1WdX2UKGgGaAloD0MIlXzsLlBLZkCUhpRSlGgVTegDaBZHQJVh3GR3eN11fZQoaAZoCWgPQwjyKJXwBDloQJSGlFKUaBVN6ANoFkdAlWQ8Of/WD3V9lChoBmgJaA9DCJNX5xiQFTtAlIaUUpRoFU0KAWgWR0CVZ4by6MBIdX2UKGgGaAloD0MIpIriVdatYkCUhpRSlGgVTegDaBZHQJVqevRqoIh1fZQoaAZoCWgPQwiXrmAb8etnQJSGlFKUaBVN6ANoFkdAlWuJwGW2PXV9lChoBmgJaA9DCDFfXoD9kmRAlIaUUpRoFU3oA2gWR0CVblVM23rldX2UKGgGaAloD0MIByeiX1sVYUCUhpRSlGgVTegDaBZHQJVyz4fwI+p1fZQoaAZoCWgPQwibyTfb3C5jQJSGlFKUaBVN6ANoFkdAlXyU4R28qXV9lChoBmgJaA9DCKrzqPg/gmJAlIaUUpRoFU3oA2gWR0CVgligkC3gdX2UKGgGaAloD0MIoffGEAApXkCUhpRSlGgVTegDaBZHQJWJvMKTjed1fZQoaAZoCWgPQwjfcB+5NThkQJSGlFKUaBVN6ANoFkdAla6jsMRYinV9lChoBmgJaA9DCH45s12hXV9AlIaUUpRoFU3oA2gWR0CVrtZbY9PldX2UKGgGaAloD0MIeJYgI6CUZUCUhpRSlGgVTegDaBZHQJW3YAZKnNx1fZQoaAZoCWgPQwiRt1z92BJnQJSGlFKUaBVN6ANoFkdAlbm4qwyIpHV9lChoBmgJaA9DCAAce/Zc8GJAlIaUUpRoFU3oA2gWR0CVuj8YyfthdX2UKGgGaAloD0MIck7sof3HY0CUhpRSlGgVTegDaBZHQJW/gGpuMuR1fZQoaAZoCWgPQwiyoZv9gYowQJSGlFKUaBVNKwFoFkdAlcDkmD15B3V9lChoBmgJaA9DCMAiv34I/mVAlIaUUpRoFU3oA2gWR0CVwb0k4WDZdX2UKGgGaAloD0MIjINLx5wtX0CUhpRSlGgVTegDaBZHQJXEBhH9WIZ1fZQoaAZoCWgPQwjiBnx+GNJnQJSGlFKUaBVN6ANoFkdAlcb7/GVAzHV9lChoBmgJaA9DCIj2sYJfOGJAlIaUUpRoFU3oA2gWR0CVybSRbKRudX2UKGgGaAloD0MIJZF9kOVkZ0CUhpRSlGgVTegDaBZHQJXKqLVFx4p1fZQoaAZoCWgPQwiDwqBMI2tgQJSGlFKUaBVN6ANoFkdAlc01lf7aZnV9lChoBmgJaA9DCDYiGAcXF2VAlIaUUpRoFU3oA2gWR0CV0XgrH2h7dX2UKGgGaAloD0MIti+gF25FYUCUhpRSlGgVTegDaBZHQJXa+BSUC7t1fZQoaAZoCWgPQwjCobd4eL9jQJSGlFKUaBVN6ANoFkdAleDZq7Ack3V9lChoBmgJaA9DCAt9sIyN/mNAlIaUUpRoFU3oA2gWR0CV6GriEQGwdX2UKGgGaAloD0MIIxCv65fAYECUhpRSlGgVTegDaBZHQJYM6T1TR6Z1fZQoaAZoCWgPQwhoQSjv45FiQJSGlFKUaBVN6ANoFkdAlhYjye7L+3V9lChoBmgJaA9DCHAIVWp2nGRAlIaUUpRoFU3oA2gWR0CWGKLfDUExdX2UKGgGaAloD0MIucX83FBbYECUhpRSlGgVTegDaBZHQJYZOxbB42V1fZQoaAZoCWgPQwg8LT9wFYxmQJSGlFKUaBVN6ANoFkdAlh7XFHavinV9lChoBmgJaA9DCE94CU79XmZAlIaUUpRoFU3oA2gWR0CWIFRpDeCTdX2UKGgGaAloD0MIsyeBzTnnZUCUhpRSlGgVTegDaBZHQJYhONo8IRh1fZQoaAZoCWgPQwibdjHNdMRZQJSGlFKUaBVN6ANoFkdAliOY4yXUpnV9lChoBmgJaA9DCFuaWyGsi2FAlIaUUpRoFU3oA2gWR0CWJsaEi+tbdX2UKGgGaAloD0MIGqTgKWStY0CUhpRSlGgVTegDaBZHQJYpgcU/OdJ1fZQoaAZoCWgPQwjPhZFe1CRaQJSGlFKUaBVN6ANoFkdAlip/kJa7mXV9lChoBmgJaA9DCCvCTUYV+mFAlIaUUpRoFU3oA2gWR0CWLRhG6PKddX2UKGgGaAloD0MIQwQcQhUnZECUhpRSlGgVTegDaBZHQJYxbtnf2sd1fZQoaAZoCWgPQwjdQlcikBRzQJSGlFKUaBVNowFoFkdAljgqoQ4CIXV9lChoBmgJaA9DCL4XX7THEV9AlIaUUpRoFU3oA2gWR0CWOzyPuG9IdX2UKGgGaAloD0MInbtdL01xRECUhpRSlGgVTQ0BaBZHQJY9MZuQ6p51fZQoaAZoCWgPQwiAngYMkpRfQJSGlFKUaBVN6ANoFkdAlkCwYgq3E3V9lChoBmgJaA9DCNZyZyYYN2JAlIaUUpRoFU3oA2gWR0CWR3hKlHjIdX2UKGgGaAloD0MIw/S9hmDWYkCUhpRSlGgVTegDaBZHQJZJeGoJiRZ1fZQoaAZoCWgPQwhU/yCSIaphQJSGlFKUaBVN6ANoFkdAlnSjv3JxN3V9lChoBmgJaA9DCLVSCOQS+1hAlIaUUpRoFU3oA2gWR0CWdwnBciW3dX2UKGgGaAloD0MIWd5VDxh2YECUhpRSlGgVTegDaBZHQJZ3mHymQ8x1fZQoaAZoCWgPQwjw+zcvzuBjQJSGlFKUaBVN6ANoFkdAln0CmqHXVnV9lChoBmgJaA9DCIOHad9cCmVAlIaUUpRoFU3oA2gWR0CWf1HOryUcdX2UKGgGaAloD0MIxRouck90ZECUhpRSlGgVTegDaBZHQJaBrollbvB1fZQoaAZoCWgPQwi+3CdHgcdmQJSGlFKUaBVN6ANoFkdAloTEOiFj/nV9lChoBmgJaA9DCBKhEWxcVGVAlIaUUpRoFU3oA2gWR0CWh5FnqVyFdX2UKGgGaAloD0MI6l4n9WUFYkCUhpRSlGgVTegDaBZHQJaIj6Q/5cl1fZQoaAZoCWgPQwhgyVUsfrhfQJSGlFKUaBVN6ANoFkdAlo+baVUuMHV9lChoBmgJaA9DCCgqG9bU22ZAlIaUUpRoFU3oA2gWR0CWlg3r2QGOdX2UKGgGaAloD0MIaoR+pl4LQkCUhpRSlGgVTRMBaBZHQJaXNH8TBZZ1fZQoaAZoCWgPQwhIUtLDUIliQJSGlFKUaBVN6ANoFkdAlpjnQhOgx3V9lChoBmgJaA9DCJj6eVMRLmJAlIaUUpRoFU3oA2gWR0CWmr12aDwpdX2UKGgGaAloD0MIUYaqmEr7YECUhpRSlGgVTegDaBZHQJaeCSJTER91fZQoaAZoCWgPQwjB5bFmZGRdQJSGlFKUaBVN6ANoFkdAlqSCPdVNpXV9lChoBmgJaA9DCH/C2a3lq2dAlIaUUpRoFU3oA2gWR0CWplr6LwWndX2UKGgGaAloD0MIW5iFdk5zQ0CUhpRSlGgVTSYBaBZHQJbOODHwPRR1fZQoaAZoCWgPQwgsRfKVQMJjQJSGlFKUaBVN6ANoFkdAltDMMmWt2nV9lChoBmgJaA9DCLZq14Q0VWJAlIaUUpRoFU3oA2gWR0CW0vZxJd0JdX2UKGgGaAloD0MIxy5RvbWvYkCUhpRSlGgVTegDaBZHQJbTeM1jy4F1fZQoaAZoCWgPQwjd7uU+OZNaQJSGlFKUaBVN6ANoFkdAltiqG1x82XV9lChoBmgJaA9DCM3LYfedH2dAlIaUUpRoFU3oA2gWR0CW2te7L+xXdX2UKGgGaAloD0MII0kQrgC2ZUCUhpRSlGgVTegDaBZHQJbdNLbpNbl1fZQoaAZoCWgPQwivIw7ZwGtmQJSGlFKUaBVN6ANoFkdAluBeDaoMrnV9lChoBmgJaA9DCM2wUdZv32FAlIaUUpRoFU3oA2gWR0CW5DK8+RozdX2UKGgGaAloD0MI0zJS76kycUCUhpRSlGgVTToDaBZHQJbrNSl3yI51fZQoaAZoCWgPQwh64c6Fke9gQJSGlFKUaBVN6ANoFkdAluwsu8K5TnV9lChoBmgJaA9DCMgMVMY/MGRAlIaUUpRoFU3oA2gWR0CW8yxwAEMcdX2UKGgGaAloD0MIpRKe0GtiZECUhpRSlGgVTegDaBZHQJb0XAsTWXl1fZQoaAZoCWgPQwi0q5Dyk49iQJSGlFKUaBVN6ANoFkdAlvvY4Ia99XV9lChoBmgJaA9DCKcC7nn+0GRAlIaUUpRoFU3oA2gWR0CXA0jgQ6IWdX2UKGgGaAloD0MIrvAuF/HIZUCUhpRSlGgVTegDaBZHQJcFd+x4Y791ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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": "Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 #1 SMP Wed Mar 2 00:30:59 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.1", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7fcf5e03f200>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcf5e03f290>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcf5e03f320>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcf5e03f3b0>", "_build": "<function ActorCriticPolicy._build at 0x7fcf5e03f440>", "forward": "<function ActorCriticPolicy.forward at 0x7fcf5e03f4d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcf5e03f560>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcf5e03f5f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcf5e03f680>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcf5e03f710>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcf5e03f7a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcf5e0869f0>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 8, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670480186952804494, "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:": "gASVkAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwiFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYi4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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": "Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-debian-bullseye-sid #1 SMP Wed Mar 2 00:30:59 UTC 2022", "Python": "3.7.12", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu117", "GPU Enabled": "True", "Numpy": "1.21.6", "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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcab213a4a987b4119a2f4ace1e09ff6264c58ed43d0a6f6f4dcb9d32710f047
|
3 |
+
size 147123
|
ppo-LunarLander-v2/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
1.6.
|
|
|
1 |
+
1.6.2
|
ppo-LunarLander-v2/data
CHANGED
@@ -1,28 +1,28 @@
|
|
1 |
{
|
2 |
"policy_class": {
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
4 |
-
":serialized:": "
|
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": "<
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
-
":serialized:": "
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
@@ -35,47 +35,47 @@
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
-
":serialized:": "
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
-
"n_envs":
|
45 |
-
"num_timesteps":
|
46 |
"_total_timesteps": 1000000,
|
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": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
-
":serialized:": "
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
@@ -86,7 +86,7 @@
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
1 |
{
|
2 |
"policy_class": {
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7fcf5e03f200>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcf5e03f290>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcf5e03f320>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcf5e03f3b0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fcf5e03f440>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fcf5e03f4d0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcf5e03f560>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fcf5e03f5f0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcf5e03f680>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcf5e03f710>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcf5e03f7a0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fcf5e0869f0>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
+
"n_envs": 8,
|
45 |
+
"num_timesteps": 1007616,
|
46 |
"_total_timesteps": 1000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1670480186952804494,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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'>",
|
63 |
+
":serialized:": "gASVkAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwiFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYi4="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.007616000000000067,
|
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'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 492,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b355b16a72b9c189faf1a7033715d2ff38119d95751fd40e5e07d320e7de428
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:120176c8a288973de16a143ccaefff772e6ded44302754f53b57f65b403cd429
|
3 |
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
OS: Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-
|
2 |
-
Python: 3.
|
3 |
-
Stable-Baselines3: 1.6.
|
4 |
-
PyTorch: 1.
|
5 |
GPU Enabled: True
|
6 |
-
Numpy: 1.
|
7 |
Gym: 0.21.0
|
|
|
1 |
+
OS: Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-debian-bullseye-sid #1 SMP Wed Mar 2 00:30:59 UTC 2022
|
2 |
+
Python: 3.7.12
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu117
|
5 |
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 273.9126905923414, "std_reward": 12.597718424250072, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T23:53:18.246473"}
|