Hugging Face's logo

KaiquanMah
/
a2c-PandaReachDense-v2

Reinforcement Learning
stable-baselines3
PandaReachDense-v2
deep-reinforcement-learning
Eval Results
Model card Files Community
1
KaiquanMah commited on
Commit
5004ffc
•
1 Parent(s): 3b9d5fd

Initial commit

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. a2c-PandaReachDense-v2.zip +1 -1
  3. replay.mp4 +0 -0
  4. results.json +1 -1
  5. vec_normalize.pkl +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PandaReachDense-v2
17
  metrics:
18
  - type: mean_reward
19
- value: -8.16 +/- 2.88
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaReachDense-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: -8.02 +/- 1.83
20
  name: mean_reward
21
  verified: false
22
  ---
a2c-PandaReachDense-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d538a00fe1e809122501a24a6eccee78958086388d18e9e66885a56ac979f79f
3
  size 107821
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b58791d38cbf98526d775e50aabb2de6d52c9eaf3e485a34f3c67a904e8becc
3
  size 107821
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -8.160378325264901, "std_reward": 2.8813114774863124, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-06T04:37:43.748841"}
 
1
+ {"mean_reward": -8.019565505255013, "std_reward": 1.8256673656297016, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-06T04:54:54.469769"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67c8b4632c6757384acd04b07b19f5147b8da29e2e31f2f58ef56c34e753e6be
3
  size 2387
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6674f06a6b6c83d68f8eff657b5540d42d5fb7c7c6c2540480ab25ec8d615203
3
  size 2387