Initial commit
Browse files- README.md +10 -4
- args.yml +16 -10
- config.yml +8 -1
- ppo-seals-CartPole-v0.zip +2 -2
- ppo-seals-CartPole-v0/_stable_baselines3_version +1 -1
- ppo-seals-CartPole-v0/data +23 -23
- ppo-seals-CartPole-v0/policy.optimizer.pth +2 -2
- ppo-seals-CartPole-v0/policy.pth +1 -1
- ppo-seals-CartPole-v0/system_info.txt +2 -2
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
|
@@ -37,15 +37,21 @@ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
|
| 37 |
|
| 38 |
```
|
| 39 |
# Download model and save it into the logs/ folder
|
| 40 |
-
python -m
|
| 41 |
python enjoy.py --algo ppo --env seals/CartPole-v0 -f logs/
|
| 42 |
```
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## Training (with the RL Zoo)
|
| 45 |
```
|
| 46 |
python train.py --algo ppo --env seals/CartPole-v0 -f logs/
|
| 47 |
# Upload the model and generate video (when possible)
|
| 48 |
-
python -m
|
| 49 |
```
|
| 50 |
|
| 51 |
## Hyperparameters
|
|
@@ -63,8 +69,8 @@ OrderedDict([('batch_size', 256),
|
|
| 63 |
('n_timesteps', 100000.0),
|
| 64 |
('policy', 'MlpPolicy'),
|
| 65 |
('policy_kwargs',
|
| 66 |
-
'
|
| 67 |
-
|
| 68 |
('vf_coef', 0.489343896591493),
|
| 69 |
('normalize', False)])
|
| 70 |
```
|
|
|
|
| 37 |
|
| 38 |
```
|
| 39 |
# Download model and save it into the logs/ folder
|
| 40 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/CartPole-v0 -orga ernestumorga -f logs/
|
| 41 |
python enjoy.py --algo ppo --env seals/CartPole-v0 -f logs/
|
| 42 |
```
|
| 43 |
|
| 44 |
+
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
| 45 |
+
```
|
| 46 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/CartPole-v0 -orga ernestumorga -f logs/
|
| 47 |
+
rl_zoo3 enjoy --algo ppo --env seals/CartPole-v0 -f logs/
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
## Training (with the RL Zoo)
|
| 51 |
```
|
| 52 |
python train.py --algo ppo --env seals/CartPole-v0 -f logs/
|
| 53 |
# Upload the model and generate video (when possible)
|
| 54 |
+
python -m rl_zoo3.push_to_hub --algo ppo --env seals/CartPole-v0 -f logs/ -orga ernestumorga
|
| 55 |
```
|
| 56 |
|
| 57 |
## Hyperparameters
|
|
|
|
| 69 |
('n_timesteps', 100000.0),
|
| 70 |
('policy', 'MlpPolicy'),
|
| 71 |
('policy_kwargs',
|
| 72 |
+
{'activation_fn': <class 'torch.nn.modules.activation.ReLU'>,
|
| 73 |
+
'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
|
| 74 |
('vf_coef', 0.489343896591493),
|
| 75 |
('normalize', False)])
|
| 76 |
```
|
args.yml
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - algo
|
| 3 |
- ppo
|
|
|
|
|
|
|
| 4 |
- - device
|
| 5 |
- cpu
|
| 6 |
- - env
|
|
@@ -12,13 +14,15 @@
|
|
| 12 |
- - eval_freq
|
| 13 |
- 25000
|
| 14 |
- - gym_packages
|
| 15 |
-
-
|
| 16 |
- - hyperparams
|
| 17 |
- null
|
| 18 |
- - log_folder
|
| 19 |
-
-
|
| 20 |
- - log_interval
|
| 21 |
- -1
|
|
|
|
|
|
|
| 22 |
- - n_eval_envs
|
| 23 |
- 1
|
| 24 |
- - n_evaluations
|
|
@@ -34,11 +38,13 @@
|
|
| 34 |
- - no_optim_plots
|
| 35 |
- false
|
| 36 |
- - num_threads
|
| 37 |
-
-
|
| 38 |
- - optimization_log_path
|
| 39 |
- null
|
| 40 |
- - optimize_hyperparameters
|
| 41 |
- false
|
|
|
|
|
|
|
| 42 |
- - pruner
|
| 43 |
- median
|
| 44 |
- - sampler
|
|
@@ -48,17 +54,15 @@
|
|
| 48 |
- - save_replay_buffer
|
| 49 |
- false
|
| 50 |
- - seed
|
| 51 |
-
-
|
| 52 |
- - storage
|
| 53 |
- null
|
| 54 |
- - study_name
|
| 55 |
- null
|
| 56 |
- - tensorboard_log
|
| 57 |
-
-
|
| 58 |
-
- - total_n_trials
|
| 59 |
-
- null
|
| 60 |
- - track
|
| 61 |
-
-
|
| 62 |
- - trained_agent
|
| 63 |
- ''
|
| 64 |
- - truncate_last_trajectory
|
|
@@ -70,6 +74,8 @@
|
|
| 70 |
- - verbose
|
| 71 |
- 1
|
| 72 |
- - wandb_entity
|
| 73 |
-
-
|
| 74 |
- - wandb_project_name
|
| 75 |
-
-
|
|
|
|
|
|
|
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - algo
|
| 3 |
- ppo
|
| 4 |
+
- - conf_file
|
| 5 |
+
- hyperparams/python/ppo.py
|
| 6 |
- - device
|
| 7 |
- cpu
|
| 8 |
- - env
|
|
|
|
| 14 |
- - eval_freq
|
| 15 |
- 25000
|
| 16 |
- - gym_packages
|
| 17 |
+
- - seals
|
| 18 |
- - hyperparams
|
| 19 |
- null
|
| 20 |
- - log_folder
|
| 21 |
+
- logs
|
| 22 |
- - log_interval
|
| 23 |
- -1
|
| 24 |
+
- - max_total_trials
|
| 25 |
+
- null
|
| 26 |
- - n_eval_envs
|
| 27 |
- 1
|
| 28 |
- - n_evaluations
|
|
|
|
| 38 |
- - no_optim_plots
|
| 39 |
- false
|
| 40 |
- - num_threads
|
| 41 |
+
- 1
|
| 42 |
- - optimization_log_path
|
| 43 |
- null
|
| 44 |
- - optimize_hyperparameters
|
| 45 |
- false
|
| 46 |
+
- - progress
|
| 47 |
+
- false
|
| 48 |
- - pruner
|
| 49 |
- median
|
| 50 |
- - sampler
|
|
|
|
| 54 |
- - save_replay_buffer
|
| 55 |
- false
|
| 56 |
- - seed
|
| 57 |
+
- 7
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
| 61 |
- null
|
| 62 |
- - tensorboard_log
|
| 63 |
+
- runs/seals/CartPole-v0__ppo__7__1670516892
|
|
|
|
|
|
|
| 64 |
- - track
|
| 65 |
+
- true
|
| 66 |
- - trained_agent
|
| 67 |
- ''
|
| 68 |
- - truncate_last_trajectory
|
|
|
|
| 74 |
- - verbose
|
| 75 |
- 1
|
| 76 |
- - wandb_entity
|
| 77 |
+
- ernestum
|
| 78 |
- - wandb_project_name
|
| 79 |
+
- seals-experts-normalized
|
| 80 |
+
- - yaml_file
|
| 81 |
+
- null
|
config.yml
CHANGED
|
@@ -24,6 +24,13 @@
|
|
| 24 |
- - policy
|
| 25 |
- MlpPolicy
|
| 26 |
- - policy_kwargs
|
| 27 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
- - vf_coef
|
| 29 |
- 0.489343896591493
|
|
|
|
| 24 |
- - policy
|
| 25 |
- MlpPolicy
|
| 26 |
- - policy_kwargs
|
| 27 |
+
- activation_fn: !!python/name:torch.nn.modules.activation.ReLU ''
|
| 28 |
+
net_arch:
|
| 29 |
+
- pi:
|
| 30 |
+
- 64
|
| 31 |
+
- 64
|
| 32 |
+
vf:
|
| 33 |
+
- 64
|
| 34 |
+
- 64
|
| 35 |
- - vf_coef
|
| 36 |
- 0.489343896591493
|
ppo-seals-CartPole-v0.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 sha256:003d7ffa0640edfa2b72507f5934a87a94e51b1b62ad13c3414db0e92a6519e6
|
| 3 |
+
size 141656
|
ppo-seals-CartPole-v0/_stable_baselines3_version
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
1.
|
|
|
|
| 1 |
+
1.6.2
|
ppo-seals-CartPole-v0/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_data object at
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {
|
|
@@ -51,27 +51,27 @@
|
|
| 51 |
},
|
| 52 |
"action_space": {
|
| 53 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 54 |
-
":serialized:": "gAWVLwsAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
| 55 |
"n": 2,
|
| 56 |
"_shape": [],
|
| 57 |
"dtype": "int64",
|
| 58 |
"_np_random": "RandomState(MT19937)"
|
| 59 |
},
|
| 60 |
-
"n_envs":
|
| 61 |
"num_timesteps": 102400,
|
| 62 |
"_total_timesteps": 100000,
|
| 63 |
"_num_timesteps_at_start": 0,
|
| 64 |
-
"seed":
|
| 65 |
"action_noise": null,
|
| 66 |
-
"start_time":
|
| 67 |
"learning_rate": {
|
| 68 |
":type:": "<class 'function'>",
|
| 69 |
-
":serialized:": "
|
| 70 |
},
|
| 71 |
-
"tensorboard_log":
|
| 72 |
"lr_schedule": {
|
| 73 |
":type:": "<class 'function'>",
|
| 74 |
-
":serialized:": "
|
| 75 |
},
|
| 76 |
"_last_obs": null,
|
| 77 |
"_last_episode_starts": {
|
|
@@ -85,7 +85,7 @@
|
|
| 85 |
"_current_progress_remaining": -0.02400000000000002,
|
| 86 |
"ep_info_buffer": {
|
| 87 |
":type:": "<class 'collections.deque'>",
|
| 88 |
-
":serialized:": "
|
| 89 |
},
|
| 90 |
"ep_success_buffer": {
|
| 91 |
":type:": "<class 'collections.deque'>",
|
|
@@ -102,9 +102,9 @@
|
|
| 102 |
"n_epochs": 10,
|
| 103 |
"clip_range": {
|
| 104 |
":type:": "<class 'function'>",
|
| 105 |
-
":serialized:": "
|
| 106 |
},
|
| 107 |
"clip_range_vf": null,
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
}
|
|
|
|
| 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 0x7f9370da4700>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9370da4790>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9370da4820>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9370da48b0>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9370da4940>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9370da49d0>",
|
| 13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9370da4a60>",
|
| 14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9370da4af0>",
|
| 15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9370da4b80>",
|
| 16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9370da4c10>",
|
| 17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9370da4ca0>",
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
+
"_abc_impl": "<_abc_data object at 0x7f9370d9cc30>"
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {
|
|
|
|
| 51 |
},
|
| 52 |
"action_space": {
|
| 53 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 54 |
+
":serialized:": "gAWVLwsAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwSX19yYW5kb21zdGF0ZV9jdG9ylJOUjAdNVDE5OTM3lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUaBOMBXN0YXRllH2UKIwDa2V5lIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolsAJAAAAAAAAAAAAgMvWU2I7QWSDdygaT5++KSAATCN90WccEqDtnFV3Y9MyLlpJIkIvbFJbpmpRHJX7SZr4rNIblBqp+ccsvAR6E3PBn61gcJfsxhg3x3PqnSmOqgLqwqIfkWzrz6Tf7NSrm1SSpbmnGNt3g/H87CT3UgGUR8+HrL79sEyK19tohIeSCjwJLlaEiqt73sZ9FJuvWOgJ3QNRV0zMGqSYGeuLv+TZ0EN3+cyUE+2SDHCnC8u+eTF8fJciknY5HW6tbE8ba0T1dJIbNDabvq3Lgzsjaj2J1a7ewVritpsjEYCurZVZpRofQC3nO0jM0C3+YuXA2lZGNYHChc8MyrCvJFQJFlfQ6BPvCeiw5+FaDMxbSonLCcRFZPKJp/lWXhgYkj0swzyhXxNK4EuHqIvN1K+tQ0O3iv/AsSiGk4LYvZONnoPxuDvSFcQq8UdUpcJew8fp98fUiPvPgHKAyO+L/60Vzkqu4hXw9hUKR7cWJQZLV9ChyDHgbsufUNTzdmm58PdxfyD8sb0Fhi30bqDkMwc6vuIXQYXYIgfYVnRcsI8ZmwcYjxg8cQeVZf1hZkd00dKZryQNLb2bz1WRqlWiK1AOV5KEPeonMRrdcwQnEBRqx9ThMDIDdCHWE2moNgX9Lu29fAxYIe//6Duh7KKhp5v80UQ7VD/0ddR8UbUVl4xVW4UneWt9U8AcBpaAgolQEZzIT0q3RzCYbWDwzLzFaawdkttUhKkFiwjDJcESKnKqKDofg5+k4YTJOSO1kagch1NV1JXrfrSfcaUDMG8F27PRTcBF/8idtyoK/uZB9ThefVNaXRCRY/K/zZz7ehTk1GSqe70bQUNaAEdFBYnd+ywk04zhEOrR532pOkyigwWnJdHBJm2VoJlaH9A04Rkw45X+ZhEcpFFBrpzhU/TBs+BgQp/ZZR1WcrWYkGzvojd9ICb8Sm3rD1jGKIuDrtw92SCXLHVCMv5Wm6IbJyVjtfO1ey/FC8aWgnTf7j/rrF5xcXoVpRipjNzX5Pc8VuvLPEPTMynVqU5M40Dr5koIKfSIg6gySM5BKS5t/zKzpo234Ril+u6/qEWjW8BdnXxw/98IhTfAUPlCXWhHyGEOF2hlQA0OG/zY0mmECbWESSFGPFOJzPNOXV/RwcT0jZ8gbecWrVBYrwJfPTHLudSMk+cb17Lwog0aT7oTB0ADU79VLykWKy8iWUGqRcsS0FMHfx4iGcxqht31heDU97MgsQJmlXKdLYP1/I6dXbpgsy/u67kQD9Gc6DjRYf6MdyDVrgymYFM18I6iwSKBIZaf0ZB1AiPK+L9N4eHDVJ1yNvscr5WfwpXg5IhpIJO7E2Rlhbh3xzcWLHo3yj4KLPpwHm2QkjDB3g+Ki/dU2++svSiw4QxzUoXT828rksNjdWXXTOoT6Uc130tGHrmbrfAVnzgUBztr1rkmZmPghFQKId2BR0FkP5MHIsn2tnq7yBXUyyvp+mIJovz5pl0thi5PXl2iiuF6NEbn1rcJ20T5r8gm1lx8gEiHeJss6lg569RDEQPP7gzAjSdS2qGZxEvnyz3QZtpWUXbNsTn+XMObH0/QYw5toa1OjO9wA6j722A5g+vSqeD4H/SOSdR/vl4+m6ZQ8ZjH04RKbGijjsHt0O438qwtwYcmyvBOgEVPUZoJsKm4xIbTANeMWUfW/9en6llQ09Q2GNGYzbPUrXjNPVTzcw7MRMwvfjqL8KSMFxRb41p/8TdxBoLL0Kl8GeA7gzPO76lQg0havYsWjS7Oihv6lY7NdC4fy/ZvTWPeicOus0EdBbVieeskgrHKNAXoP8f/8MT2Kfh5aG69pUbV60nurbRfvbxAQp7QY1LHpt9wdiNBHrmXapt1i9ujL40360NSK5qm9zNaW0EF79jlogPKlKxZI3MMzLpD9a/TxRRQCbc2K+kYySF2kmJWtbyC383WeVDjimpDXpDTPng23MBKrwP+ZU5SynDdFY59LM/DdidhSjcBqa6d0uHGivnMXdui4qFwj1M3fkqCda0ks0pyoNTL9x6ORZZwLL3l6A3sNruF9bVyLi1KSnsE/umc0nRu3EPtaMLzo3ltupslyMhR2aMVjgxE9qykusS4Q9K/wMBItytZsaIg9J9C/SE4w/SSWtq/FT0Tky+uDkGCtR/ESEt0G9ldpIsQTGEO5JXn7MvPOK6elxfmcFxnn5Wegq9zY0lVOaYpuTkeFtSDEJCKDu2AMEjpgXs13GEd7vcDJgl7i3uQaSJWOFaK+l51C6R77PVNOFl/jAHq+Diu+K2PhI6xodlk2ZZNsPYEFyZC+zzkiczrIxx4xx8T0WsCWYZEQMums3oxrEwdQqqbrrPmQSs07U+JfaagHlzslMbmbqiZ/9VXWQjxyfVlGjuM1qxgqeSHyVwvKl6f6DbkpOoYlTnRU9g3C1FENK717sF5/fZbbQMNqsJuaGvpqf57LLRKt/XFPDjHDUB9pbPM1r0TLH5KG74ICd43JrtiaCgNXJxHkYyzKrXQAx/XvilvzBvNLsrDUaoMvlT9ijtcF8dTjTB+U6sP7eAXA0BbuZW+EylZ66meD1auuTfd0MfWNxggoAj3px8RCXRyJkOqxjTgrgUGflH8TjL4mJSsrd9MCQoAqwmN8CrrLff3nlT3YhXUsXXNSI7lqBxXsy2OTNgHlHZmYfLg+67h3KnjOexQhueOod2KqF7EsJNcscbpywzWZmEx66XZre2BVKEbFJnQG0B9GOxbw8T1fGhwRrMuNpprpFRYE7Cir5MNHd7U7JCpO2J9mIKRaeHMdlu8wGONMGAJYjxNKFrJjvc2lFG4yXDmOMxpzYx8jAEFnKRCzlohYowX63r30lQ4KO/+nCK12rJ6Ev2TdjF+bL6tXybdp0eNo+5+MlTDa407XyUrOv6ve6iZTSZvvK9h6M/DFP/JFhv1CmcmlKYYF5oF1chTIAZiG4S+uH/Zn/hw4j9cjKhWCjhViTrooipaq6pyhd1CXpzXXodGrsmlrYX9e47fikDqRsw06oJCUGni5RqsyZWZizGL7GqQlNzsxSRWioTQh0IAEDkhV/Tg3NCJbL6dV7h4idhehjvMc9wki3ApcdPoz3QxY3jHak0bQGkXnRUa+8tsH9zttnNH66piW6P++i1LUHsmpkMLrtOKLDFAW72M8tpJm8I0A7dSD7VO/llyhZN45fvyOyq/h93CJr+tpGqzKWRJZ2n1OekXsEx5jMtdpWGkxn51Xu206pxf9ZmEONv3kabS+LJblwnigtqyvI/nbvWVzBYR4H38BjJgszCdfpqdEJXN+CD/0cWG1uvD4Eq6VRFAt2+kNUgP7ZeKlGgJjAJ1NJSJiIeUUpQoSwNoDU5OTkr/////Sv////9LAHSUYk1wAoWUjAFDlHSUUpSMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVidWIu",
|
| 55 |
"n": 2,
|
| 56 |
"_shape": [],
|
| 57 |
"dtype": "int64",
|
| 58 |
"_np_random": "RandomState(MT19937)"
|
| 59 |
},
|
| 60 |
+
"n_envs": 1,
|
| 61 |
"num_timesteps": 102400,
|
| 62 |
"_total_timesteps": 100000,
|
| 63 |
"_num_timesteps_at_start": 0,
|
| 64 |
+
"seed": 1,
|
| 65 |
"action_noise": null,
|
| 66 |
+
"start_time": 1670516894814637504,
|
| 67 |
"learning_rate": {
|
| 68 |
":type:": "<class 'function'>",
|
| 69 |
+
":serialized:": "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"
|
| 70 |
},
|
| 71 |
+
"tensorboard_log": "runs/seals/CartPole-v0__ppo__7__1670516892/seals-CartPole-v0",
|
| 72 |
"lr_schedule": {
|
| 73 |
":type:": "<class 'function'>",
|
| 74 |
+
":serialized:": "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"
|
| 75 |
},
|
| 76 |
"_last_obs": null,
|
| 77 |
"_last_episode_starts": {
|
|
|
|
| 85 |
"_current_progress_remaining": -0.02400000000000002,
|
| 86 |
"ep_info_buffer": {
|
| 87 |
":type:": "<class 'collections.deque'>",
|
| 88 |
+
":serialized:": "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"
|
| 89 |
},
|
| 90 |
"ep_success_buffer": {
|
| 91 |
":type:": "<class 'collections.deque'>",
|
|
|
|
| 102 |
"n_epochs": 10,
|
| 103 |
"clip_range": {
|
| 104 |
":type:": "<class 'function'>",
|
| 105 |
+
":serialized:": "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"
|
| 106 |
},
|
| 107 |
"clip_range_vf": null,
|
| 108 |
+
"normalize_advantage": true,
|
| 109 |
+
"target_kl": null
|
| 110 |
}
|
ppo-seals-CartPole-v0/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 sha256:5f8f95042d63d71329a83889b244855b119ff1fde42470577638bb8a7472455e
|
| 3 |
+
size 82425
|
ppo-seals-CartPole-v0/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40513
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:385b42f25c52b68029dd9c47cf3b1b779c3ec4a4441606218bacd6091fa5bb6f
|
| 3 |
size 40513
|
ppo-seals-CartPole-v0/system_info.txt
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
-
OS: Linux-5.4.0-
|
| 2 |
Python: 3.8.10
|
| 3 |
-
Stable-Baselines3: 1.
|
| 4 |
PyTorch: 1.11.0+cu102
|
| 5 |
GPU Enabled: False
|
| 6 |
Numpy: 1.22.3
|
|
|
|
| 1 |
+
OS: Linux-5.4.0-125-generic-x86_64-with-glibc2.29 #141-Ubuntu SMP Wed Aug 10 13:42:03 UTC 2022
|
| 2 |
Python: 3.8.10
|
| 3 |
+
Stable-Baselines3: 1.6.2
|
| 4 |
PyTorch: 1.11.0+cu102
|
| 5 |
GPU Enabled: False
|
| 6 |
Numpy: 1.22.3
|
replay.mp4
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 sha256:4b7051380170d8c8c4a86101d6def7c0b8950e420b0bbd4775b96c1e170313aa
|
| 3 |
+
size 60768
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-
|
|
|
|
| 1 |
+
{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T14:33:46.683447"}
|
train_eval_metrics.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 sha256:913814bce3741222e544117345a87cf5fd970bd301ff0985679b10763887659e
|
| 3 |
+
size 6702
|