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:
+- RiverraidNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+ results:
+ - task:
+ type: reinforcement-learning
+ name: reinforcement-learning
+ dataset:
+ name: RiverraidNoFrameskip-v4
+ type: RiverraidNoFrameskip-v4
+ metrics:
+ - type: mean_reward
+ value: 6583.00 +/- 765.35
+ name: mean_reward
+ verified: false
+---
+
+# **PPO** Agent playing **RiverraidNoFrameskip-v4**
+This is a trained model of a **PPO** agent playing **RiverraidNoFrameskip-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 RiverraidNoFrameskip-v4 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env RiverraidNoFrameskip-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 RiverraidNoFrameskip-v4 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env RiverraidNoFrameskip-v4 -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env RiverraidNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env RiverraidNoFrameskip-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 +1,77 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+ - ppo
+ - - device
+ - auto
+ - - env
+ - RiverraidNoFrameskip-v4
+ - - env_kwargs
+ - null
+ - - eval_episodes
+ - 20
+ - - eval_freq
+ - 100000
+ - - gym_packages
+ - []
+ - - hyperparams
+ - n_envs: 8
+ - - 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
+ - 200000000
+ - - n_trials
+ - 500
+ - - no_optim_plots
+ - false
+ - - num_threads
+ - 1
+ - - optimization_log_path
+ - null
+ - - optimize_hyperparameters
+ - false
+ - - pruner
+ - median
+ - - sampler
+ - tpe
+ - - save_freq
+ - -1
+ - - save_replay_buffer
+ - false
+ - - seed
+ - 3987763893
+ - - 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
+ - - 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-RiverraidNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45abde82ad8874f22625089ffcddf1e22676314ebeaa9ef66e88b09d607da0de
+size 20518852

ppo-RiverraidNoFrameskip-v4/_stable_baselines3_version

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

ppo-RiverraidNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73199f3c61f40ad658c1abbad7ca4cc0c3ac9f0a5b6aaf9ada60c7d7d4fde775
+size 13560761

ppo-RiverraidNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a3be73c2e9d3de09c407e28ba6caf3aa94a134a6673ad55bd3da30828c118f
+size 6782465

ppo-RiverraidNoFrameskip-v4/pytorch_variables.pth

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

ppo-RiverraidNoFrameskip-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 sha256:8eb984c138796be97444725726f0d82161f0a235b91f18af9d7778896450dd92
+size 248565

results.json

@@ -0,0 +1 @@
+{"mean_reward": 6583.0, "std_reward": 765.3502466191541, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:12:17.821093"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1d326ea41bd3869380745fdd7185b8aba990a2d3781abfd8196def17a4b10b
+size 167175