Upload folder using huggingface_hub

.gitattributes

@@ -25,6 +25,7 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
@@ -32,4 +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
-replay.mp4 filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,138 +1,87 @@
 ---
-library_name: rl-algo-impls
+library_name: stable-baselines3
 tags:
 - SpaceInvadersNoFrameskip-v4
-- a2c
 - deep-reinforcement-learning
 - reinforcement-learning
+- stable-baselines3
 model-index:
-- name: a2c
+- name: DQN
   results:
-  - metrics:
-    - type: mean_reward
-      value: 1084.06 +/- 245.28
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: SpaceInvadersNoFrameskip-v4
       type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 713.50 +/- 96.83
+      name: mean_reward
+      verified: false
 ---
-# **A2C** Agent playing **SpaceInvadersNoFrameskip-v4**
-
-This is a trained model of a **A2C** agent playing **SpaceInvadersNoFrameskip-v4** using the [/sgoodfriend/rl-algo-impls](https://github.com/sgoodfriend/rl-algo-impls) repo.
-
-All models trained at this commit can be found at https://api.wandb.ai/links/sgoodfriend/ysd5gj7p.
 
-## Training Results
+# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
+This is a trained model of a **DQN** 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).
 
-This model was trained from 3 trainings of **A2C** agents using different initial seeds. These agents were trained by checking out [983cb75](https://github.com/sgoodfriend/rl-algo-impls/tree/983cb75e43e51cf4ef57f177194ab9a4a1a8808b). The best and last models were kept from each training. This submission has loaded the best models from each training, reevaluates them, and selects the best model from these latest evaluations (mean - std).
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
 
-| algo   | env                         |   seed |   reward_mean |   reward_std |   eval_episodes | best   | wandb_url                                                                    |
-|:-------|:----------------------------|-------:|--------------:|-------------:|----------------:|:-------|:-----------------------------------------------------------------------------|
-| a2c    | SpaceInvadersNoFrameskip-v4 |      1 |      1084.06  |      245.282 |              16 | *      | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/1xnaha2m) |
-| a2c    | SpaceInvadersNoFrameskip-v4 |      2 |       911.562 |      127.937 |              16 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/2ikwmahh) |
-| a2c    | SpaceInvadersNoFrameskip-v4 |      3 |      1034.06  |      354.746 |              16 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/n9pubrvf) |
+## 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
+SBX (SB3 + Jax): https://github.com/araffin/sbx
 
-### Prerequisites: Weights & Biases (WandB)
-Training and benchmarking assumes you have a Weights & Biases project to upload runs to.
-By default training goes to a rl-algo-impls project while benchmarks go to
-rl-algo-impls-benchmarks. During training and benchmarking runs, videos of the best
-models and the model weights are uploaded to WandB.
-
-Before doing anything below, you'll need to create a wandb account and run `wandb
-login`.
-
-
-
-## Usage
-/sgoodfriend/rl-algo-impls: https://github.com/sgoodfriend/rl-algo-impls
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
 
-Note: While the model state dictionary and hyperaparameters are saved, the latest
-implementation could be sufficiently different to not be able to reproduce similar
-results. You might need to checkout the commit the agent was trained on:
-[983cb75](https://github.com/sgoodfriend/rl-algo-impls/tree/983cb75e43e51cf4ef57f177194ab9a4a1a8808b).
 ```
-# Downloads the model, sets hyperparameters, and runs agent for 3 episodes
-python enjoy.py --wandb-run-path=sgoodfriend/rl-algo-impls-benchmarks/1xnaha2m
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Kolosok -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
-Setup hasn't been completely worked out yet, so you might be best served by using Google
-Colab starting from the
-[colab_enjoy.ipynb](https://github.com/sgoodfriend/rl-algo-impls/blob/main/colab_enjoy.ipynb)
-notebook.
-
-
-
-## Training
-If you want the highest chance to reproduce these results, you'll want to checkout the
-commit the agent was trained on: [983cb75](https://github.com/sgoodfriend/rl-algo-impls/tree/983cb75e43e51cf4ef57f177194ab9a4a1a8808b). While
-training is deterministic, different hardware will give different results.
-
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
 ```
-python train.py --algo a2c --env SpaceInvadersNoFrameskip-v4 --seed 1
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Kolosok -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
-Setup hasn't been completely worked out yet, so you might be best served by using Google
-Colab starting from the
-[colab_train.ipynb](https://github.com/sgoodfriend/rl-algo-impls/blob/main/colab_train.ipynb)
-notebook.
-
-
-
-## Benchmarking (with Lambda Labs instance)
-This and other models from https://api.wandb.ai/links/sgoodfriend/ysd5gj7p were generated by running a script on a Lambda
-Labs instance. In a Lambda Labs instance terminal:
+## Training (with the RL Zoo)
 ```
-git clone git@github.com:sgoodfriend/rl-algo-impls.git
-cd rl-algo-impls
-bash ./lambda_labs/setup.sh
-wandb login
-bash ./lambda_labs/benchmark.sh [-a {"ppo a2c dqn vpg"}] [-e ENVS] [-j {6}] [-p {rl-algo-impls-benchmarks}] [-s {"1 2 3"}]
+python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Kolosok
 ```
 
-### Alternative: Google Colab Pro+
-As an alternative,
-[colab_benchmark.ipynb](https://github.com/sgoodfriend/rl-algo-impls/tree/main/benchmarks#:~:text=colab_benchmark.ipynb),
-can be used. However, this requires a Google Colab Pro+ subscription and running across
-4 separate instances because otherwise running all jobs will exceed the 24-hour limit.
-
-
-
 ## Hyperparameters
-This isn't exactly the format of hyperparams in hyperparams/a2c.yml, but instead the Wandb Run Config. However, it's very
-close and has some additional data:
+```python
+OrderedDict([('batch_size', 32),
+             ('buffer_size', 100000),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('exploration_final_eps', 0.01),
+             ('exploration_fraction', 0.1),
+             ('frame_stack', 4),
+             ('gradient_steps', 1),
+             ('learning_rate', 0.0001),
+             ('learning_starts', 100000),
+             ('n_timesteps', 1000000.0),
+             ('optimize_memory_usage', False),
+             ('policy', 'CnnPolicy'),
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
+             ('normalize', False)])
 ```
-additional_keys_to_log: []
-algo: a2c
-algo_hyperparams:
-  ent_coef: 0.01
-  vf_coef: 0.25
-device: auto
-env: SpaceInvadersNoFrameskip-v4
-env_hyperparams:
-  frame_stack: 4
-  n_envs: 16
-  no_reward_fire_steps: 500
-  no_reward_timeout_steps: 1000
-  vec_env_class: async
-env_id: null
-eval_hyperparams: {}
-microrts_reward_decay_callback: false
-n_timesteps: 10000000
-policy_hyperparams:
-  activation_fn: relu
-seed: 1
-use_deterministic_algorithms: true
-wandb_entity: null
-wandb_group: null
-wandb_project_name: rl-algo-impls-benchmarks
-wandb_tags:
-- benchmark_983cb75
-- host_129-159-43-75
-- branch_main
-- v0.0.9
 
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
 ```

args.yml

@@ -0,0 +1,85 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - dqn.yml
+  - - device
+    - auto
+  - - env
+    - SpaceInvadersNoFrameskip-v4
+  - - env_kwargs
+    - null
+  - - eval_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
+    - 381900577
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - trial_id
+    - null
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 32
+  - - buffer_size
+    - 100000
+  - - env_wrapper
+    - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - exploration_final_eps
+    - 0.01
+  - - exploration_fraction
+    - 0.1
+  - - frame_stack
+    - 4
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - 0.0001
+  - - learning_starts
+    - 100000
+  - - n_timesteps
+    - 1000000.0
+  - - optimize_memory_usage
+    - false
+  - - policy
+    - CnnPolicy
+  - - target_update_interval
+    - 1000
+  - - train_freq
+    - 4

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19ccbc80cb66b553a31d2a9002979b6a26b042528dd4c29fbe45c099a632b7d
+size 27219597

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.7.0

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af50457e5905a4c41e80a1f79a6714359b5a6a8928a5473cbeef81e03dec23c
+size 13506569

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84dc331d0e18ccb562ff95fc23280a9bb6e7398b33cb0cc551bb53d1fd073dc5
+size 13505767

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c7431cf6005e7d8f367d79e995f63e2f9b981a37e3437b795d058f9af4308b
+size 1261

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025
+- Python: 3.12.12
+- Stable-Baselines3: 2.7.0
+- PyTorch: 2.8.0+cu126
+- GPU Enabled: True
+- Numpy: 2.0.2
+- Cloudpickle: 3.1.1
+- Gymnasium: 1.2.1
+- OpenAI Gym: 0.25.2

env_kwargs.yml

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

results.json

@@ -0,0 +1 @@
+{"mean_reward": 713.5, "std_reward": 96.82587464102764, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-15T11:24:26.433149"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cff95733983b1ee63368d93b9973880c7c408c0fc4bf47eadc8f6d95c6e3a1
+size 36876