Initial commit

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: stable-baselines3
 tags:
-- SpaceInvadersNoFrameskip-v4
+- BreakoutNoFrameskip-v4
 - deep-reinforcement-learning
 - reinforcement-learning
 - stable-baselines3
@@ -12,17 +12,17 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: SpaceInvadersNoFrameskip-v4
-      type: SpaceInvadersNoFrameskip-v4
+      name: BreakoutNoFrameskip-v4
+      type: BreakoutNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 14.50 +/- 12.34
+      value: 47.20 +/- 13.51
       name: mean_reward
       verified: false
 ---
 
-# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
-This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
+# **DQN** Agent playing **BreakoutNoFrameskip-v4**
+This is a trained model of a **DQN** agent playing **BreakoutNoFrameskip-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).
 
@@ -38,21 +38,21 @@ 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 kaiosinimbu -f logs/
-python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env BreakoutNoFrameskip-v4 -orga kaiosinimbu -f logs/
+python enjoy.py --algo dqn --env BreakoutNoFrameskip-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 kaiosinimbu -f logs/
-rl_zoo3 enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env BreakoutNoFrameskip-v4 -orga kaiosinimbu -f logs/
+rl_zoo3 enjoy --algo dqn --env BreakoutNoFrameskip-v4  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+python train.py --algo dqn --env BreakoutNoFrameskip-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 kaiosinimbu
+python -m rl_zoo3.push_to_hub --algo dqn --env BreakoutNoFrameskip-v4 -f logs/ -orga kaiosinimbu
 ```
 
 ## Hyperparameters
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 100000.0),
+             ('n_timesteps', 500000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -6,7 +6,7 @@
   - - device
     - auto
   - - env
-    - SpaceInvadersNoFrameskip-v4
+    - BreakoutNoFrameskip-v4
   - - env_kwargs
     - null
   - - eval_episodes
@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 2099344128
+    - 1317383280
   - - storage
     - null
   - - study_name

config.yml

@@ -18,7 +18,7 @@
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 100000.0
+    - 500000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-BreakoutNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ae43bf8ef4fe00c806cab699327fb84a775ec7809c61861d9cc6b8bd855e49
+size 27208401

dqn-BreakoutNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

dqn-BreakoutNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49a384027d947233a9744f1c102f95f3d333fc1f12337b69f6012965a7e2651
+size 13497547

dqn-BreakoutNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1066457d7bbee64840bb86c4c6c98d72177eae8a65eaf5f937a7a8d76e9c3b
+size 13496745

dqn-BreakoutNoFrameskip-v4/pytorch_variables.pth

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

dqn-BreakoutNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.8.15
+Stable-Baselines3: 1.6.2
+PyTorch: 1.12.1+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25fcb8f4cd387bbd8ea8f1869dda23f9bc38859fa045e4ba505c96295aab752b
-size 275554
+oid sha256:4425d8f04e4832a4ac4d89814f01b75d2f69942abd5b9159138e7685ffb758fc
+size 77950

results.json

@@ -1 +1 @@
-{"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T15:50:29.278608"}
+{"mean_reward": 47.2, "std_reward": 13.51147660324363, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T16:37:02.036241"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb05dba770e5feefafed8f2510fbd126ca700f8a8148ac753a678bf06cc8708f
-size 5729
+oid sha256:45951ddaf7d28df1c2f1c8a777847753945d831e86d06e9b9194864320daf2e5
+size 32318