Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: QRDQN
+- name: DQN
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 1059.00 +/- 439.89
+      value: 1415.00 +/- 538.76
       name: mean_reward
       verified: false
 ---
 
-# **QRDQN** Agent playing **SpaceInvadersNoFrameskip-v4**
-This is a trained model of a **QRDQN** 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).
 
@@ -43,33 +43,39 @@ pip install rl_zoo3
 
 ```
 # Download model and save it into the logs/ folder
-python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga Mihail-P -f logs/
-python -m rl_zoo3.enjoy --algo qrdqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga iblub -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 qrdqn --env SpaceInvadersNoFrameskip-v4 -orga Mihail-P -f logs/
-python -m rl_zoo3.enjoy --algo qrdqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga iblub -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 qrdqn --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 qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Mihail-P
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga iblub
 ```
 
 ## Hyperparameters
 ```python
 OrderedDict([('batch_size', 64),
-             ('buffer_size', 150000),
+             ('buffer_size', 1000000),
              ('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
-             ('exploration_fraction', 0.025),
+             ('exploration_final_eps', 0.01),
+             ('exploration_fraction', 0.1),
              ('frame_stack', 4),
+             ('gradient_steps', 1),
+             ('learning_rate', 0.0001),
+             ('learning_starts', 100000),
              ('n_timesteps', 10000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
              ('normalize', False)])
 ```

args.yml

@@ -1,6 +1,6 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
-    - qrdqn
+    - dqn
   - - conf_file
     - null
   - - device
@@ -10,15 +10,13 @@
   - - env_kwargs
     - null
   - - eval_episodes
-    - 25
+    - 5
   - - eval_freq
-    - 50000
+    - 25000
   - - gym_packages
     - []
   - - hyperparams
-    - batch_size: 64
-      buffer_size: 150000
-      exploration_fraction: 0.025
+    - null
   - - log_folder
     - logs/
   - - log_interval
@@ -34,7 +32,7 @@
   - - n_startup_trials
     - 10
   - - n_timesteps
-    - 10000000
+    - -1
   - - n_trials
     - 500
   - - no_optim_plots
@@ -52,17 +50,17 @@
   - - sampler
     - tpe
   - - save_freq
-    - 1000000
+    - -1
   - - save_replay_buffer
     - false
   - - seed
-    - 1078690446
+    - 4025715748
   - - storage
     - null
   - - study_name
     - null
   - - tensorboard_log
-    - /tblogs/
+    - ''
   - - track
     - false
   - - trained_agent
@@ -81,3 +79,5 @@
     - sb3
   - - wandb_tags
     - []
+  - - yaml_file
+    - null

config.yml

@@ -2,16 +2,28 @@
 - - - batch_size
     - 64
   - - buffer_size
-    - 150000
+    - 1000000
   - - env_wrapper
     - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - exploration_final_eps
+    - 0.01
   - - exploration_fraction
-    - 0.025
+    - 0.1
   - - frame_stack
     - 4
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - 0.0001
+  - - learning_starts
+    - 100000
   - - n_timesteps
     - 10000000.0
   - - 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 sha256:24630ac98b56c5dc42d4aae85747ae6b5fab29381690872dda5ebdbd419d092a
+size 27225058

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

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

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c3fd998273dfced9ec8feec6560589ca1e93c5e24ade1c7e314f4db8accd78
+size 13505739

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf07d1709c8b2913a90712f213e1122bb396af1b862a3df90158c73d0bc58915
+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-5.10.147+-x86_64-with-debian-bullseye-sid # 1 SMP Sat Oct 15 09:06:22 UTC 2022
+- Python: 3.7.12
+- Stable-Baselines3: 1.7.0
+- 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 sha256:74e2345a1acfdab0aec4c523b3687dc651e457d5651afaa63b93b3a961116455
-size 558346
+oid sha256:00a2e690c5cfe8966f2a19dddea16690551733c093fea228ede9db056da72f06
+size 207801

results.json

@@ -1 +1 @@
-{"mean_reward": 1059.0, "std_reward": 439.89089556388865, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-17T06:17:02.113019"}
+{"mean_reward": 1415.0, "std_reward": 538.7624708533436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-12T09:05:13.918172"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c462cb45c3f36e46ef59f3ac324b4caaab97d843b88a0ce88468d2b40dfb97c7
-size 308560
+oid sha256:d3f2c8ce8ee92fc53ec7eb7d1b9a158b8d8090b125824a4538b2f3345f139810
+size 230379