Push agent to the 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 +1,48 @@
+---
+tags:
+- Deathmatch-v1
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Deathmatch-v1
+      type: Deathmatch-v1
+    metrics:
+    - type: mean_reward
+      value: 46.57 +/- 30.63
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing Deathmatch-v1
+
+  This is a trained model of a PPO agent playing Deathmatch-v1.
+
+  # Hyperparameters
+  ```python
+  {'env_id': 'Deathmatch-v1'
+'num_envs': 96
+'num_steps': 96
+'learning_rate': 5e-05
+'learning_rate_min': 1e-05
+'gamma': 0.99
+'gae_lambda': 0.95
+'clip_coef': 0.2
+'total_timesteps': 30000000
+'recurrence': 32
+'ent_coef': 0.001
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'num_minibatches': 4
+'update_epochs': 1
+'frame_skip': 4}
+  ```
+  

logs/events.out.tfevents.1722890875.tf-notebook-0.332.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b60baa7b337260ca6455afcee71dd11cc42ffd03e536b6c1a850376ac3f670c
+size 1182692

logs/events.out.tfevents.1722903405.tf-notebook-0.332.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030079dba3215cd2d2680fba363924839756ae99ee4f3310f0edb3104b7eacf4
+size 272206

logs/events.out.tfevents.1722904492.tf-notebook-0.5430.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d865eed1b4533e24f23909d20e0c2bda9eaa1cc8cf5995078d5a6d4deee79c3
+size 103133

logs/events.out.tfevents.1722904913.tf-notebook-0.5979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0025b03732c5b4d72fe6aaee64b21033ea424ba4e18a79a30e2e59d48db4364f
+size 2038465

logs/events.out.tfevents.1722914780.tf-notebook-0.6674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f6b4d1d4fbdcf0dd2c8feb4c48ba4e9a9796b4a43de842a82a86fe0c19264c
+size 2038465

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50867e84ebd74c8339d1dd46d8acf29593409bf095c3696d6a5a4bbda7e9f599
+size 13031730

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187b6e805b364acf1e890826edeac4faaa80ec82a286de1a98b8779c6f43366c
+size 22578093

results.json

@@ -0,0 +1 @@
+{"env_id": "Deathmatch-v1", "mean_reward": 46.570068359375, "std_reward": 30.63079071044922, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-06T13:31:59.000132"}