Initial Commit
Browse files- README.md +21 -1
- args.yml +7 -21
- ppo-CartPole-v1.zip +2 -2
- ppo-CartPole-v1/data +34 -33
- ppo-CartPole-v1/policy.optimizer.pth +1 -1
- ppo-CartPole-v1/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +3 -0
README.md
CHANGED
|
@@ -23,7 +23,11 @@ model-index:
|
|
| 23 |
# **PPO** Agent playing **CartPole-v1**
|
| 24 |
This is a trained model of a **PPO** agent playing **CartPole-v1**
|
| 25 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
| 26 |
-
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
## Usage (with SB3 RL Zoo)
|
| 29 |
|
|
@@ -43,3 +47,19 @@ python train.py --algo ppo --env CartPole-v1 -f logs/
|
|
| 43 |
# Upload the model and generate video (when possible)
|
| 44 |
python -m utils.push_to_hub --algo ppo --env CartPole-v1 -f logs/ -orga sb3
|
| 45 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
# **PPO** Agent playing **CartPole-v1**
|
| 24 |
This is a trained model of a **PPO** agent playing **CartPole-v1**
|
| 25 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
| 26 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
| 27 |
+
|
| 28 |
+
The RL Zoo is a training framework for Stable Baselines3
|
| 29 |
+
reinforcement learning agents,
|
| 30 |
+
with hyperparameter optimization and pre-trained agents included.
|
| 31 |
|
| 32 |
## Usage (with SB3 RL Zoo)
|
| 33 |
|
|
|
|
| 47 |
# Upload the model and generate video (when possible)
|
| 48 |
python -m utils.push_to_hub --algo ppo --env CartPole-v1 -f logs/ -orga sb3
|
| 49 |
```
|
| 50 |
+
|
| 51 |
+
## Hyperparameters
|
| 52 |
+
```python
|
| 53 |
+
OrderedDict([('batch_size', 256),
|
| 54 |
+
('clip_range', 'lin_0.2'),
|
| 55 |
+
('ent_coef', 0.0),
|
| 56 |
+
('gae_lambda', 0.8),
|
| 57 |
+
('gamma', 0.98),
|
| 58 |
+
('learning_rate', 'lin_0.001'),
|
| 59 |
+
('n_envs', 8),
|
| 60 |
+
('n_epochs', 20),
|
| 61 |
+
('n_steps', 32),
|
| 62 |
+
('n_timesteps', 100000.0),
|
| 63 |
+
('policy', 'MlpPolicy'),
|
| 64 |
+
('normalize', False)])
|
| 65 |
+
```
|
args.yml
CHANGED
|
@@ -1,28 +1,24 @@
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - algo
|
| 3 |
- ppo
|
| 4 |
-
- - device
|
| 5 |
-
- auto
|
| 6 |
- - env
|
| 7 |
- CartPole-v1
|
| 8 |
- - env_kwargs
|
| 9 |
- null
|
| 10 |
- - eval_episodes
|
| 11 |
-
-
|
| 12 |
- - eval_freq
|
| 13 |
-
-
|
| 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
|
| 25 |
-
-
|
| 26 |
- - n_jobs
|
| 27 |
- 1
|
| 28 |
- - n_startup_trials
|
|
@@ -30,13 +26,9 @@
|
|
| 30 |
- - n_timesteps
|
| 31 |
- -1
|
| 32 |
- - n_trials
|
| 33 |
-
-
|
| 34 |
-
- - no_optim_plots
|
| 35 |
-
- false
|
| 36 |
- - num_threads
|
| 37 |
- -1
|
| 38 |
-
- - optimization_log_path
|
| 39 |
-
- null
|
| 40 |
- - optimize_hyperparameters
|
| 41 |
- false
|
| 42 |
- - pruner
|
|
@@ -48,26 +40,20 @@
|
|
| 48 |
- - save_replay_buffer
|
| 49 |
- false
|
| 50 |
- - seed
|
| 51 |
-
-
|
| 52 |
- - storage
|
| 53 |
- null
|
| 54 |
- - study_name
|
| 55 |
- null
|
| 56 |
- - tensorboard_log
|
| 57 |
- ''
|
| 58 |
-
- - track
|
| 59 |
-
- false
|
| 60 |
- - trained_agent
|
| 61 |
- ''
|
| 62 |
- - truncate_last_trajectory
|
| 63 |
- true
|
| 64 |
- - uuid
|
| 65 |
-
-
|
| 66 |
- - vec_env
|
| 67 |
- dummy
|
| 68 |
- - verbose
|
| 69 |
- 1
|
| 70 |
-
- - wandb_entity
|
| 71 |
-
- null
|
| 72 |
-
- - wandb_project_name
|
| 73 |
-
- sb3
|
|
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - algo
|
| 3 |
- ppo
|
|
|
|
|
|
|
| 4 |
- - env
|
| 5 |
- CartPole-v1
|
| 6 |
- - env_kwargs
|
| 7 |
- null
|
| 8 |
- - eval_episodes
|
| 9 |
+
- 10
|
| 10 |
- - eval_freq
|
| 11 |
+
- 10000
|
| 12 |
- - gym_packages
|
| 13 |
- []
|
| 14 |
- - hyperparams
|
| 15 |
- null
|
| 16 |
- - log_folder
|
| 17 |
+
- rl-trained-agents/
|
| 18 |
- - log_interval
|
| 19 |
- -1
|
|
|
|
|
|
|
| 20 |
- - n_evaluations
|
| 21 |
+
- 20
|
| 22 |
- - n_jobs
|
| 23 |
- 1
|
| 24 |
- - n_startup_trials
|
|
|
|
| 26 |
- - n_timesteps
|
| 27 |
- -1
|
| 28 |
- - n_trials
|
| 29 |
+
- 10
|
|
|
|
|
|
|
| 30 |
- - num_threads
|
| 31 |
- -1
|
|
|
|
|
|
|
| 32 |
- - optimize_hyperparameters
|
| 33 |
- false
|
| 34 |
- - pruner
|
|
|
|
| 40 |
- - save_replay_buffer
|
| 41 |
- false
|
| 42 |
- - seed
|
| 43 |
+
- 1648070233
|
| 44 |
- - storage
|
| 45 |
- null
|
| 46 |
- - study_name
|
| 47 |
- null
|
| 48 |
- - tensorboard_log
|
| 49 |
- ''
|
|
|
|
|
|
|
| 50 |
- - trained_agent
|
| 51 |
- ''
|
| 52 |
- - truncate_last_trajectory
|
| 53 |
- true
|
| 54 |
- - uuid
|
| 55 |
+
- true
|
| 56 |
- - vec_env
|
| 57 |
- dummy
|
| 58 |
- - verbose
|
| 59 |
- 1
|
|
|
|
|
|
|
|
|
|
|
|
ppo-CartPole-v1.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:aed1e01e30eda8663abaa93e78d6112e34d477a6dbb8fc2f7f6b244d589aec95
|
| 3 |
+
size 139223
|
ppo-CartPole-v1/data
CHANGED
|
@@ -4,78 +4,75 @@
|
|
| 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": {},
|
| 23 |
"observation_space": {
|
| 24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 25 |
-
":serialized:": "gAWVdwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////
|
| 26 |
"dtype": "float32",
|
| 27 |
-
"_shape": [
|
| 28 |
-
4
|
| 29 |
-
],
|
| 30 |
"low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
|
| 31 |
"high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
|
| 32 |
"bounded_below": "[ True True True True]",
|
| 33 |
"bounded_above": "[ True True True True]",
|
| 34 |
-
"_np_random": null
|
|
|
|
|
|
|
|
|
|
| 35 |
},
|
| 36 |
"action_space": {
|
| 37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 38 |
-
":serialized:": "
|
| 39 |
"n": 2,
|
| 40 |
-
"_shape": [],
|
| 41 |
"dtype": "int64",
|
| 42 |
-
"_np_random": "RandomState(MT19937)"
|
|
|
|
| 43 |
},
|
| 44 |
"n_envs": 8,
|
| 45 |
-
"num_timesteps":
|
| 46 |
"_total_timesteps": 100000,
|
| 47 |
"_num_timesteps_at_start": 0,
|
| 48 |
"seed": 0,
|
| 49 |
"action_noise": null,
|
| 50 |
-
"start_time":
|
| 51 |
"learning_rate": {
|
| 52 |
":type:": "<class 'function'>",
|
| 53 |
-
":serialized:": "
|
| 54 |
},
|
| 55 |
"tensorboard_log": null,
|
| 56 |
"lr_schedule": {
|
| 57 |
":type:": "<class 'function'>",
|
| 58 |
-
":serialized:": "
|
| 59 |
},
|
| 60 |
"_last_obs": null,
|
| 61 |
-
"_last_episode_starts":
|
| 62 |
-
":type:": "<class 'numpy.ndarray'>",
|
| 63 |
-
":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
|
| 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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 77 |
},
|
| 78 |
-
"_n_updates":
|
| 79 |
"n_steps": 32,
|
| 80 |
"gamma": 0.98,
|
| 81 |
"gae_lambda": 0.8,
|
|
@@ -86,9 +83,13 @@
|
|
| 86 |
"n_epochs": 20,
|
| 87 |
"clip_range": {
|
| 88 |
":type:": "<class 'function'>",
|
| 89 |
-
":serialized:": "
|
| 90 |
},
|
| 91 |
"clip_range_vf": null,
|
| 92 |
"normalize_advantage": true,
|
| 93 |
-
"target_kl": null
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
}
|
|
|
|
| 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 0x7f66a4faba70>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f66a4fabb00>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f66a4fabb90>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f66a4fabc20>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f66a4fabcb0>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f66a4fabd40>",
|
| 13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f66a4fabdd0>",
|
| 14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f66a4fabe60>",
|
| 15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f66a4fabef0>",
|
| 16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f66a4fabf80>",
|
| 17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f66a4fb2050>",
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
+
"_abc_impl": "<_abc_data object at 0x7f66a4fff660>"
|
| 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 |
"low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
|
| 28 |
"high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
|
| 29 |
"bounded_below": "[ True True True True]",
|
| 30 |
"bounded_above": "[ True True True True]",
|
| 31 |
+
"_np_random": null,
|
| 32 |
+
"_shape": [
|
| 33 |
+
4
|
| 34 |
+
]
|
| 35 |
},
|
| 36 |
"action_space": {
|
| 37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 38 |
+
":serialized:": "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",
|
| 39 |
"n": 2,
|
|
|
|
| 40 |
"dtype": "int64",
|
| 41 |
+
"_np_random": "RandomState(MT19937)",
|
| 42 |
+
"_shape": []
|
| 43 |
},
|
| 44 |
"n_envs": 8,
|
| 45 |
+
"num_timesteps": 100096,
|
| 46 |
"_total_timesteps": 100000,
|
| 47 |
"_num_timesteps_at_start": 0,
|
| 48 |
"seed": 0,
|
| 49 |
"action_noise": null,
|
| 50 |
+
"start_time": 1614619329.118938,
|
| 51 |
"learning_rate": {
|
| 52 |
":type:": "<class 'function'>",
|
| 53 |
+
":serialized:": "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"
|
| 54 |
},
|
| 55 |
"tensorboard_log": null,
|
| 56 |
"lr_schedule": {
|
| 57 |
":type:": "<class 'function'>",
|
| 58 |
+
":serialized:": "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"
|
| 59 |
},
|
| 60 |
"_last_obs": null,
|
| 61 |
+
"_last_episode_starts": null,
|
|
|
|
|
|
|
|
|
|
| 62 |
"_last_original_obs": null,
|
| 63 |
"_episode_num": 0,
|
| 64 |
"use_sde": false,
|
| 65 |
"sde_sample_freq": -1,
|
| 66 |
+
"_current_progress_remaining": -0.0009600000000000719,
|
| 67 |
"ep_info_buffer": {
|
| 68 |
":type:": "<class 'collections.deque'>",
|
| 69 |
+
":serialized:": "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"
|
| 70 |
},
|
| 71 |
"ep_success_buffer": {
|
| 72 |
":type:": "<class 'collections.deque'>",
|
| 73 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 74 |
},
|
| 75 |
+
"_n_updates": 7820,
|
| 76 |
"n_steps": 32,
|
| 77 |
"gamma": 0.98,
|
| 78 |
"gae_lambda": 0.8,
|
|
|
|
| 83 |
"n_epochs": 20,
|
| 84 |
"clip_range": {
|
| 85 |
":type:": "<class 'function'>",
|
| 86 |
+
":serialized:": "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"
|
| 87 |
},
|
| 88 |
"clip_range_vf": null,
|
| 89 |
"normalize_advantage": true,
|
| 90 |
+
"target_kl": null,
|
| 91 |
+
"_last_dones": {
|
| 92 |
+
":type:": "<class 'numpy.ndarray'>",
|
| 93 |
+
":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
|
| 94 |
+
}
|
| 95 |
}
|
ppo-CartPole-v1/policy.optimizer.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 79453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe8d3c93141198d72b36b61520a65759eb4489de111095126f9193177aaea525
|
| 3 |
size 79453
|
ppo-CartPole-v1/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:af07ce9863e1c063cbd8af21ff152b6226ff46fdb9878b61d7383f3335aceac6
|
| 3 |
size 40513
|
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 sha256:973039e99274e465f44e6680454d85ec49645c67c509e92183c7a6d1a570d977
|
| 3 |
+
size 56189
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-
|
|
|
|
| 1 |
+
{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-24T17:08:02.211559"}
|
train_eval_metrics.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e8043022605666a30a0cdf8af15258e591c5cb9e475e3812131f824656f5e43
|
| 3 |
+
size 10190
|