Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,29 @@
+---
+tags:
+- MontezumaRevengeNoFrameskip-v4
+- RND
+- CNN
+- reinforcement-learning
+- custom-implementation
+- atari
+- MontezumaRevengeNoFrameskip-v4
+model-index:
+- name: RND-MontezumaRevengeNoframeSkip-v4
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MontezumaRevengeNoFrameskip-v4
+      type: MontezumaRevengeNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 60.00 +/- 149.67
+      name: mean_reward
+      verified: false
+---
+
+  # **RND with CNN** Agent playing **MontezumaRevengeNoFrameskip-v4**
+  This is a trained model of a **RND-CNN** agent playing **MontezumaRevengeNoFrameskip-v4** .
+  To learn to use this model and train yours check this notebook on kaggle: https://www.kaggle.com/code/syedjarullahhisham/drl-extra-personal-unit-5-rnd-montezuma-mario-bros
+  

agent.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d17eef042235eba953472a459d080041e1df0951d2df6c09805d2061e8ce1b
+size 21177478

hyperparameters.json

@@ -0,0 +1 @@
+{"trainmethod": "RND", "envid": "MontezumaRevengeNoFrameskip-v4", "maxstepperepisode": 4500, "learningrate": 0.0001, "numenv": 1, "numstep": 128, "gamma": 0.999, "intgamma": 0.99, "lambda": 0.95, "usegae": true, "clipgradnorm": 0.5, "entropy": 0.001, "epoch": 4, "minibatch": 4, "ppoeps": 0.1, "extcoef": 2.0, "intcoef": 1.0, "stickyaction": false, "actionprob": 0.25, "lifedone": false, "obsnormstep": 50}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc9698b46aa0f98741d013623f2ac3bcdb85e63ca851a4e6fde4ba90c419d7f
+size 5655334

results.json

@@ -0,0 +1 @@
+{"env_id": "MontezumaRevengeNoFrameskip-v4", "mean_reward": 60.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-23T06:53:37.640281"}