pushing model

Browse files

Files changed (9) hide show

.gitattributes +3 -0
README.md +2 -2
events.out.tfevents.1700813949.4090-171.1715869.0 → events.out.tfevents.1704452191.4090-171.100792.0 +2 -2
ppo_fix_continuous_action.cleanrl_model +0 -0
ppo_fix_continuous_action.py +1 -1
replay.mp4 +2 -2
videos/{Ant-v4__ppo_fix_continuous_action__1__1700813942-eval → Ant-v4__ppo_fix_continuous_action__1__1704452176-eval}/rl-video-episode-0.mp4 +2 -2
videos/{Ant-v4__ppo_fix_continuous_action__1__1700813942-eval → Ant-v4__ppo_fix_continuous_action__1__1704452176-eval}/rl-video-episode-1.mp4 +2 -2
videos/{Ant-v4__ppo_fix_continuous_action__1__1700813942-eval → Ant-v4__ppo_fix_continuous_action__1__1704452176-eval}/rl-video-episode-8.mp4 +2 -2

.gitattributes CHANGED Viewed

@@ -37,3 +37,6 @@ videos/Ant-v4__ppo_fix_continuous_action__1__1700813942-eval/rl-video-episode-8.
 videos/Ant-v4__ppo_fix_continuous_action__1__1700813942-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Ant-v4__ppo_fix_continuous_action__1__1700813942-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
 replay.mp4 filter=lfs diff=lfs merge=lfs -text

 videos/Ant-v4__ppo_fix_continuous_action__1__1700813942-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Ant-v4__ppo_fix_continuous_action__1__1700813942-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
 replay.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Ant-v4__ppo_fix_continuous_action__1__1704452176-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Ant-v4__ppo_fix_continuous_action__1__1704452176-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Ant-v4__ppo_fix_continuous_action__1__1704452176-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ model-index:
       type: Ant-v4
     metrics:
     - type: mean_reward
-      value: 2038.72 +/- 1159.89
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ curl -OL https://huggingface.co/sdpkjc/Ant-v4-ppo_fix_continuous_action-seed1/ra
 curl -OL https://huggingface.co/sdpkjc/Ant-v4-ppo_fix_continuous_action-seed1/raw/main/pyproject.toml
 curl -OL https://huggingface.co/sdpkjc/Ant-v4-ppo_fix_continuous_action-seed1/raw/main/poetry.lock
 poetry install --all-extras
-python ppo_fix_continuous_action.py --save-model --hf-entity sdpkjc --seed 1 --upload-model --track --env-id Ant-v4
 ```
 # Hyperparameters

       type: Ant-v4
     metrics:
     - type: mean_reward
+      value: 1568.39 +/- 831.28
       name: mean_reward
       verified: false
 ---
 curl -OL https://huggingface.co/sdpkjc/Ant-v4-ppo_fix_continuous_action-seed1/raw/main/pyproject.toml
 curl -OL https://huggingface.co/sdpkjc/Ant-v4-ppo_fix_continuous_action-seed1/raw/main/poetry.lock
 poetry install --all-extras
+python ppo_fix_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id Ant-v4 --seed 1 --track
 ```
 # Hyperparameters

events.out.tfevents.1700813949.4090-171.1715869.0 → events.out.tfevents.1704452191.4090-171.100792.0 RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375ed2443c0f4ee7954abcfdeaaae16846373ecd74bb9e6c1d009f6054ce19f2
-size 810084

 version https://git-lfs.github.com/spec/v1
+oid sha256:fc4c40114b0a688bcb92a4ede9e8437cafb2039eb7030eb7358fb996d9ce8705
+size 786648

ppo_fix_continuous_action.cleanrl_model CHANGED Viewed

Binary files a/ppo_fix_continuous_action.cleanrl_model and b/ppo_fix_continuous_action.cleanrl_model differ

ppo_fix_continuous_action.py CHANGED Viewed

@@ -430,7 +430,7 @@ if __name__ == "__main__":
             # https://github.com/DLR-RM/stable-baselines3/pull/658
             for idx, trunc in enumerate(truncations):
-                if trunc:
                     real_next_obs = infos["final_observation"][idx]
                     with torch.no_grad():
                         terminal_value = agent.get_value(torch.Tensor(real_next_obs).to(device)).reshape(1, -1)[0][0]

             # https://github.com/DLR-RM/stable-baselines3/pull/658
             for idx, trunc in enumerate(truncations):
+                if trunc and not terminations[idx]:
                     real_next_obs = infos["final_observation"][idx]
                     with torch.no_grad():
                         terminal_value = agent.get_value(torch.Tensor(real_next_obs).to(device)).reshape(1, -1)[0][0]

replay.mp4 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f574965b021043c6ad0d8836e1d00c37b9615d734da218f9ca2fe4ee87ad986
-size 2137603

 version https://git-lfs.github.com/spec/v1
+oid sha256:403f054222dad4eed191a90df0c63ded1b392790f9975c06deac36eb420b366a
+size 2158605

videos/{Ant-v4__ppo_fix_continuous_action__1__1700813942-eval → Ant-v4__ppo_fix_continuous_action__1__1704452176-eval}/rl-video-episode-0.mp4 RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336f34d5ad8af0c628c57300b7ad98cad66e16c69dd50bf76b6ea545738028e6
-size 1998175

 version https://git-lfs.github.com/spec/v1
+oid sha256:637855f9dac709e465f6c171a08bb9a9bd14f2f92d9d98c41b6d7df9ae2aaafb
+size 2330533

videos/{Ant-v4__ppo_fix_continuous_action__1__1700813942-eval → Ant-v4__ppo_fix_continuous_action__1__1704452176-eval}/rl-video-episode-1.mp4 RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc0870acc5f5ac469972f7ca5d1260688b1f073bd9a8644e3c7ab848d0d1b23
-size 2007661

 version https://git-lfs.github.com/spec/v1
+oid sha256:e13c496feaf4e3e73b53c15f81c739f4187dd75c562ee1e389461d4f168b11ac
+size 1759145

videos/{Ant-v4__ppo_fix_continuous_action__1__1700813942-eval → Ant-v4__ppo_fix_continuous_action__1__1704452176-eval}/rl-video-episode-8.mp4 RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f574965b021043c6ad0d8836e1d00c37b9615d734da218f9ca2fe4ee87ad986
-size 2137603

 version https://git-lfs.github.com/spec/v1
+oid sha256:403f054222dad4eed191a90df0c63ded1b392790f9975c06deac36eb420b366a
+size 2158605