Upload folder using huggingface_hub

README.md

@@ -1,12 +1,11 @@
 ---
 tags:
-- Pixelcopter-PLE-v0
 - actor-critic
 - reinforcement-learning
-- custom-implementation
 - deep-rl-class
+- Pixelcopter-PLE-v0
 model-index:
-- name: ActorCritic-Pixelcopter-PLE-v0
+- name: ActorCritic-Pixelcopter
   results:
   - task:
       type: reinforcement-learning
@@ -16,17 +15,14 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 41.45 +/- 39.02
+      value: 31.84 +/- 22.63
       name: mean_reward
       verified: false
 ---
 
 # **Actor-Critic** Agent playing **Pixelcopter-PLE-v0**
-
 This is a trained model of an **Actor-Critic** agent playing **Pixelcopter-PLE-v0**.
 This model was trained as part of the Deep Reinforcement Learning Course.
-
 ## Evaluation Results
-
-- **Mean Reward:** 41.45 +/- 39.02
-- **Final Score (mean_reward - std_reward):** 2.43
+- **Mean Reward:** 31.84 +/- 22.63
+- **Final Score (mean_reward - std_reward):** 9.21

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 256, "n_training_episodes": 20000, "n_evaluation_episodes": 20, "max_t": 1000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0"}
+{"h_size": 256, "n_training_episodes": 20000, "n_evaluation_episodes": 25, "max_t": 1000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0"}

model.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102bf27677b81c5ab63a21c0187ae9d88e28de7ee7907292477b9698910a7b99
+oid sha256:fc7cd031726ed5f9f5e6433fe1ddb47545dfc11089fec9a679d9d07e54dacd84
 size 277224