Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,89 @@
+---
+library_name: stable-baselines3
+tags:
+- PongNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PongNoFrameskip-v4
+      type: PongNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: -21.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **PongNoFrameskip-v4**
+This is a trained model of a **PPO** agent playing **PongNoFrameskip-v4**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo ppo --env PongNoFrameskip-v4 -orga hishamcse -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env PongNoFrameskip-v4  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo ppo --env PongNoFrameskip-v4 -orga hishamcse -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env PongNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env PongNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env PongNoFrameskip-v4 -f logs/ -orga hishamcse
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('clip_range', 0.4),
+             ('ent_coef', 1.6077823351479547e-08),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('frame_stack', 4),
+             ('gae_lambda', 0.9342974216877361),
+             ('gamma', 0.999),
+             ('learning_rate', 0.009929843682975054),
+             ('n_envs', 8),
+             ('n_epochs', 9),
+             ('n_steps', 128),
+             ('n_timesteps', 5000000.0),
+             ('normalize', False),
+             ('policy', 'CnnPolicy'),
+             ('policy_kwargs',
+              'dict(net_arch=[dict(pi=[64, 64], vf=[64, '
+              '64]),],activation_fn=nn.Tanh)'),
+             ('vf_coef', 0.7945615838365445)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - ppo.yml
+  - - device
+    - auto
+  - - env
+    - PongNoFrameskip-v4
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs/
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3607532832
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,33 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - clip_range
+    - 0.4
+  - - ent_coef
+    - 1.6077823351479547e-08
+  - - env_wrapper
+    - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - frame_stack
+    - 4
+  - - gae_lambda
+    - 0.9342974216877361
+  - - gamma
+    - 0.999
+  - - learning_rate
+    - 0.009929843682975054
+  - - n_envs
+    - 8
+  - - n_epochs
+    - 9
+  - - n_steps
+    - 128
+  - - n_timesteps
+    - 5000000.0
+  - - normalize
+    - false
+  - - policy
+    - CnnPolicy
+  - - policy_kwargs
+    - dict(net_arch=[dict(pi=[64, 64], vf=[64, 64]),],activation_fn=nn.Tanh)
+  - - vf_coef
+    - 0.7945615838365445

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

ppo-PongNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc4d7ec8496a44372be1f8023d8fbc5b347339bfe751116941b261c48860743
+size 21303123

ppo-PongNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.2

ppo-PongNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0175b27ecd683ea4388fdd3be684c13e861332ea1ec4ff7424d623ba0d6f6ed
+size 14085346

ppo-PongNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5277ae3a4364a4f8b48de0abe0ab64e93327622e919daaa6b7613e1c3d19f83a
+size 7044698

ppo-PongNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-PongNoFrameskip-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023
+- Python: 3.10.13
+- Stable-Baselines3: 2.3.2
+- PyTorch: 2.1.2
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.0
+- OpenAI Gym: 0.26.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53947da4050e7a0021804d7be4a778a52cfe07267d7d17e131e8a0d7c33eb6ae
+size 48922

results.json

@@ -0,0 +1 @@
+{"mean_reward": -21.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-15T13:23:09.103295"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d2c41779906768f9bd8955147134f1ae8c54772970b733a3fe395725e0ca774
+size 15028