Initial commit

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: PPO
+- name: DQN
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 171.00 +/- 74.79
+      value: 465.00 +/- 117.88
       name: mean_reward
       verified: false
 ---
 
-# **PPO** Agent playing **SpaceInvadersNoFrameskip-v4**
-This is a trained model of a **PPO** agent playing **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).
 
@@ -43,39 +43,41 @@ pip install rl_zoo3
 
 ```
 # Download model and save it into the logs/ folder
-python -m rl_zoo3.load_from_hub --algo ppo --env SpaceInvadersNoFrameskip-v4 -orga Meyssank -f logs/
-python -m rl_zoo3.enjoy --algo ppo --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Meyssank -f logs/
+python -m rl_zoo3.enjoy --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 ppo --env SpaceInvadersNoFrameskip-v4 -orga Meyssank -f logs/
-python -m rl_zoo3.enjoy --algo ppo --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Meyssank -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python -m rl_zoo3.train --algo ppo --env SpaceInvadersNoFrameskip-v4 -f logs/
+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 ppo --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Meyssank
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Meyssank
 ```
 
 ## Hyperparameters
 ```python
 OrderedDict([('batch_size', 256),
-             ('clip_range', 0.001),
-             ('ent_coef', 0.01),
+             ('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),
-             ('n_envs', 8),
-             ('n_epochs', 4),
-             ('n_steps', 128),
-             ('n_timesteps', 100000.0),
-             ('normalize', False),
+             ('learning_starts', 100000),
+             ('n_timesteps', 1000000.0),
+             ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
-             ('vf_coef', 0.5)])
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
+             ('normalize', False)])
 ```
 
 # Environment Arguments

args.yml

@@ -1,8 +1,8 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
-    - ppo
+    - dqn
   - - conf_file
-    - ppo.yaml
+    - dqn.yaml
   - - device
     - auto
   - - env
@@ -56,7 +56,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 2571120557
+    - 3983418881
   - - storage
     - null
   - - study_name

config.yml

@@ -1,27 +1,29 @@
 !!python/object/apply:collections.OrderedDict
 - - - batch_size
     - 256
-  - - clip_range
-    - 0.001
-  - - ent_coef
-    - 0.01
+  - - 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
-  - - n_envs
-    - 8
-  - - n_epochs
-    - 4
-  - - n_steps
-    - 128
+  - - learning_starts
+    - 100000
   - - n_timesteps
-    - 100000.0
-  - - normalize
+    - 1000000.0
+  - - optimize_memory_usage
     - false
   - - policy
     - CnnPolicy
-  - - vf_coef
-    - 0.5
+  - - 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:bee25d3666e2f39a518371ea7fc953d73e262fa427462435f69e312cd3a1ef77
+size 27220729

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.4.0a7

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851faae6e89740ee953858cbe9a4593a2c170ad095c1ab061c4998d1d383797f
+size 13506172

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abda0bffb22bd88867236114b485281855455d49375c95301d3fe79083c742a3
+size 13505370

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.4.0a7
+- PyTorch: 2.4.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bccce4863e6938906fb8d09baacbd2c617489d9ea570b2e73acb32157ad566d
-size 250913
+oid sha256:816b0f30579a74c135f36eba95521f81d65cbf44552235dd90eb5e1da649d7dc
+size 237673

results.json

@@ -1 +1 @@
-{"mean_reward": 171.0, "std_reward": 74.79304780526061, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-03T19:50:11.227363"}
+{"mean_reward": 465.0, "std_reward": 117.87705459503134, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-03T22:39:33.144001"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe5fb6ec3bd3884b5e4383f57ed4dbba051bc346cf256de0c7cc937bcb1cf020
-size 6912
+oid sha256:498ed6aad42c82b32fa4faa3176165ff2ae93c040908539e97c2d1d3aed1c20c
+size 39694