Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,79 @@
+---
+library_name: stable-baselines3
+tags:
+- QbertNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: QbertNoFrameskip-v4
+      type: QbertNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 11580.00 +/- 2709.58
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **QbertNoFrameskip-v4**
+This is a trained model of a **PPO** agent playing **QbertNoFrameskip-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 QbertNoFrameskip-v4 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env QbertNoFrameskip-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 QbertNoFrameskip-v4 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env QbertNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env QbertNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env QbertNoFrameskip-v4 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('clip_range', 'lin_0.1'),
+             ('ent_coef', 0.01),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('frame_stack', 4),
+             ('learning_rate', 'lin_2.5e-4'),
+             ('n_envs', 8),
+             ('n_epochs', 4),
+             ('n_steps', 128),
+             ('n_timesteps', 10000000.0),
+             ('policy', 'CnnPolicy'),
+             ('vf_coef', 0.5),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - QbertNoFrameskip-v4
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - 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
+    - 1105060133
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/QbertNoFrameskip-v4__ppo__1105060133__1675437934
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - qgallouedec
+  - - wandb_project_name
+    - sb3-iqn
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - clip_range
+    - lin_0.1
+  - - ent_coef
+    - 0.01
+  - - env_wrapper
+    - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - frame_stack
+    - 4
+  - - learning_rate
+    - lin_2.5e-4
+  - - n_envs
+    - 8
+  - - n_epochs
+    - 4
+  - - n_steps
+    - 128
+  - - n_timesteps
+    - 10000000.0
+  - - policy
+    - CnnPolicy
+  - - vf_coef
+    - 0.5

env_kwargs.yml

@@ -0,0 +1 @@
+{}

ppo-QbertNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f695662c58c10b0d682fe32397682bbe76604efbcfa63539ad10906ab5730b
+size 20445209

ppo-QbertNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

ppo-QbertNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1232a22ec2c7d863ed3ffb66b0a8bdd725dfadc0ac959f3aff2b67991f1c1eca
+size 13511481

ppo-QbertNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4d8bd44562174a1eb9c114175662914632c4845c598e907cd8596d0b0a649d
+size 6757825

ppo-QbertNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-QbertNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b261ed6be25f2c249b3c80e3bff7ae318daba95ed1d6b209288e1ab402d2b6
+size 205641

results.json

@@ -0,0 +1 @@
+{"mean_reward": 11580.0, "std_reward": 2709.584839048226, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T19:43:53.052905"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a054d4a7b3ce33e72e82c0520bfbdc1f69d1cc124c7e062c0c4bb179566a2d41
+size 424245