Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -3.91 +/- 0.88
+      value: -2.72 +/- 0.96
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d068866eec36c0e289fb47da4677b2a0f311c7775376e95f5409b340a6b95117
+oid sha256:6e45f7965389dfabe8e5a2bb62d27858bbf0ce17ecec7c10d841e78a81225477
 size 107818

results.json

@@ -1 +1 @@
-{"mean_reward": -3.9131251045502724, "std_reward": 0.8840966866374826, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-27T22:05:32.649239"}
+{"mean_reward": -2.7170423437841236, "std_reward": 0.9581316354552158, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-27T22:08:05.713417"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e53957a27015dc126e0c5f602f666bff002b96172f25445b050a14ee63ccc3
+oid sha256:f577dc7204a14072d24992e2cd609e38f0f461956673e4dd3a5a07127a0affce
 size 2387