2nd commit

.gitattributes

@@ -2,11 +2,13 @@
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.npy filter=lfs diff=lfs merge=lfs -text
@@ -20,6 +22,7 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
+*.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
 *.tflite filter=lfs diff=lfs merge=lfs -text
@@ -27,6 +30,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard 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

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 210.00 +/- 145.89
+      value: 562.00 +/- 92.42
       name: mean_reward
       verified: false
 ---
@@ -43,13 +43,13 @@ pip install rl_zoo3
 
 ```
 # Download model and save it into the logs/ folder
-python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga reachrkr -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga dineshresearch -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 dqn --env SpaceInvadersNoFrameskip-v4 -orga reachrkr -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga dineshresearch -f logs/
 python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
@@ -57,7 +57,7 @@ python -m rl_zoo3.enjoy --algo dqn --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 dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga reachrkr
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga dineshresearch
 ```
 
 ## Hyperparameters
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 100000.0),
+             ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 2794116141
+    - 2115956098
   - - storage
     - null
   - - study_name

config.yml

@@ -18,7 +18,7 @@
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 100000.0
+    - 1000000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5d698f7e0387732d291f05a32b81ac651d1a68f2693feb3d88fc75e596425c5
-size 13719746
+oid sha256:717a588e45d5ceb619a3a3734a0a26e967f2566e839a4b9fdec01ef72bf9b383
+size 27224807

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
-size 687
+oid sha256:c7c1b37b19a251e7770eb0c75e9e073fc174219b7fd47bda8bad73c04a80f635
+size 13505739

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9cfcd9e1766805f72358e8889b276d0318eca05e35400bbf4bdc770bb354005
+oid sha256:76fedabee2addf0f00776109d73599f94d39390b0d268384b25ba245d0e7a53a
 size 13504937

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -3,5 +3,5 @@
 - Stable-Baselines3: 1.8.0a2
 - PyTorch: 1.13.1+cu116
 - GPU Enabled: True
-- Numpy: 1.21.6
+- Numpy: 1.22.4
 - Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e38cee50b413c4b8cdda5a1434709b6fd57234bbadab18c33a59a732db44e643
-size 255939
+oid sha256:7a3f07c5303853d0728e0684857b05e17920782cdcb5361567ac8927489c34fa
+size 202273

results.json

@@ -1 +1 @@
-{"mean_reward": 210.0, "std_reward": 145.89379698945393, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-29T22:38:26.926819"}
+{"mean_reward": 562.0, "std_reward": 92.41753080449618, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-08T16:28:49.763824"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0570b193c78251d11188d295befaabb70a340db45aaf1effcd1fd2aa78d91b
-size 5845
+oid sha256:2ce75a56fdd4d63757460939e069ffb167df6ca3faed071e26eac01c9c48df6a
+size 36758