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 +1,82 @@
+---
+library_name: stable-baselines3
+tags:
+- SpaceInvadersNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: SpaceInvadersNoFrameskip-v4
+      type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 780.00 +/- 273.77
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **SpaceInvadersNoFrameskip-v4**
+This is a trained model of a **A2C** agent playing **SpaceInvadersNoFrameskip-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 a2c --env SpaceInvadersNoFrameskip-v4 -orga araffin -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env SpaceInvadersNoFrameskip-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 a2c --env SpaceInvadersNoFrameskip-v4 -orga araffin -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env SpaceInvadersNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo a2c --env SpaceInvadersNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo a2c --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga araffin
+```
+
+## 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)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

a2c-SpaceInvadersNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44485d1226a0c3f2f5a2f47abf8e123dd96d7b79c6dd4a73518d19cf93ccfa1
+size 13678930

a2c-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a10

a2c-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b28e2d6f968629988c4be0062eb2348d2752ad0800e505990c91bbcf638685
+size 6754305

a2c-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5bad6d33794aba63c5f360592ae15f71f15dfcde5e0632a7217829469371d41
+size 6757825

a2c-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

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

a2c-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.14.21-150400.24.46-default-x86_64-with-glibc2.31 # 1 SMP PREEMPT_DYNAMIC Thu Feb 9 08:38:18 UTC 2023 (2d95137)
+- Python: 3.9.13
+- Stable-Baselines3: 2.0.0a10
+- PyTorch: 2.0.1
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.0
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - a2c
+  - - env
+    - SpaceInvadersNoFrameskip-v4
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - 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
+    - 910364921
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - 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 @@
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e7fe0a7773c1d06f01bc151d98e36799ac4f28018646787ec64083e0e90875
+size 225551

results.json

@@ -0,0 +1 @@
+{"mean_reward": 780.0, "std_reward": 273.76997644007645, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-25T17:54:34.309170"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:115a43e39f25722eef7418aae2e7b7c997c429f9c688d5583e1b563442602eef
+size 493767