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 +1,77 @@
+---
+library_name: stable-baselines3
+tags:
+- SpaceInvadersNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 374.00 +/- 214.89
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: SpaceInvadersNoFrameskip-v4
+      type: SpaceInvadersNoFrameskip-v4
+---
+
+# **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).
+
+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 rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga bitcloud2 -f logs/
+python enjoy.py --algo dqn --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 dqn --env SpaceInvadersNoFrameskip-v4 -orga bitcloud2 -f logs/
+rl_zoo3 enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --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 bitcloud2
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 32),
+             ('buffer_size', 400000),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('exploration_final_eps', 0.01),
+             ('exploration_fraction', 0.1),
+             ('frame_stack', 4),
+             ('gamma', 0.99),
+             ('gradient_steps', 1),
+             ('learning_rate', 0.0001),
+             ('learning_starts', 200000),
+             ('n_timesteps', 10000.0),
+             ('normalize', False),
+             ('optimize_memory_usage', True),
+             ('policy', 'CnnPolicy'),
+             ('replay_buffer_kwargs', {'handle_timeout_termination': False}),
+             ('target_update_interval', 30000),
+             ('train_freq', 4)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - SpaceInvadersNoFrameskip-v4
+  - - 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
+    - 1375423501
+  - - 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 +1,35 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 32
+  - - buffer_size
+    - 400000
+  - - env_wrapper
+    - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - exploration_final_eps
+    - 0.01
+  - - exploration_fraction
+    - 0.1
+  - - frame_stack
+    - 4
+  - - gamma
+    - 0.99
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - 0.0001
+  - - learning_starts
+    - 200000
+  - - n_timesteps
+    - 10000.0
+  - - normalize
+    - false
+  - - optimize_memory_usage
+    - true
+  - - policy
+    - CnnPolicy
+  - - replay_buffer_kwargs
+    - handle_timeout_termination: false
+  - - target_update_interval
+    - 30000
+  - - train_freq
+    - 4

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f951f8f3f5f6d3a4fc0f1ac4057e49ecc67a92e6ccfaa05c3ce4651c83be07
+size 13716431

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0a10

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
+size 687

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e5f8d4448e066e274c79fb49d46d2ebf9ad1bb034d013f01f286be5563f98d
+size 13504937

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

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

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-1086-aws-x86_64-with-glibc2.29 #93~18.04.1-Ubuntu SMP Fri Sep 23 17:19:00 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.7.0a10
+PyTorch: 1.13.1+cu117
+GPU Enabled: True
+Numpy: 1.22.4
+Gym: 0.21.0

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d34ed105eab5ee73699dbb8875f126b9b92306bf6863b1e4f282176699efe65
+size 234682

results.json

@@ -0,0 +1 @@
+{"mean_reward": 374.0, "std_reward": 214.89299662855464, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-24T00:16:51.830706"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec6c5bfd75114c877a3712ed60ff73aa2fd8f66192813967d44aae22416f302
+size 600