Initial commit

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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 +1,65 @@
+---
+library_name: stable-baselines3
+tags:
+- PongNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 17.10 +/- 2.70
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PongNoFrameskip-v4
+      type: PongNoFrameskip-v4
+---
+
+# **A2C** Agent playing **PongNoFrameskip-v4**
+This is a trained model of a **A2C** 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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo a2c --env PongNoFrameskip-v4 -orga sb3 -f logs/
+python enjoy.py --algo a2c --env PongNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo a2c --env PongNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo a2c --env PongNoFrameskip-v4 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('ent_coef', 0.01),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('frame_stack', 4),
+             ('n_envs', 16),
+             ('n_timesteps', 10000000.0),
+             ('policy', 'CnnPolicy'),
+             ('policy_kwargs',
+              'dict(optimizer_class=RMSpropTFLike, '
+              'optimizer_kwargs=dict(eps=1e-5))'),
+             ('vf_coef', 0.25),
+             ('normalize', False)])
+```

a2c-PongNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67282364498b3eac2964323fe99374405cbe37203cd7aedaa502cd512b3a70cb
+size 13682775

a2c-PongNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

a2c-PongNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5433a1a9005e7056ea1d5a069a5d67988cfbe4b28188a53c10aa585ffea4fafd
+size 6754305

a2c-PongNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c987075bab588857c894aa025b498ec65ac9014e8dff26a7f3c7b6b5e54bd4
+size 6755009

a2c-PongNoFrameskip-v4/pytorch_variables.pth

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

a2c-PongNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - a2c
+  - - env
+    - PongNoFrameskip-v4
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 50000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3504351757
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - subproc
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,17 @@
+!!python/object/apply:collections.OrderedDict
+- - - ent_coef
+    - 0.01
+  - - env_wrapper
+    - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - frame_stack
+    - 4
+  - - n_envs
+    - 16
+  - - n_timesteps
+    - 10000000.0
+  - - policy
+    - CnnPolicy
+  - - policy_kwargs
+    - dict(optimizer_class=RMSpropTFLike, optimizer_kwargs=dict(eps=1e-5))
+  - - vf_coef
+    - 0.25

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875a318e81dcc38b3b463c76eca5b0d326405d36a48836cf31af5e4fa6b2907e
+size 70985

results.json

@@ -0,0 +1 @@
+{"mean_reward": 17.1, "std_reward": 2.7, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T17:16:04.937548"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1564cf7d4db2317102f8b86bcdbe8706ee104a42e3f575a3354ad7dc3e11d15b
+size 186167