Push Reinforce agent to the Hub

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.001, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3}
+{"h_size": 512, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.05, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a995edaa763da386bc366b7114970990b90b69b8f86325ea249f44fbc62ec2e0
-size 144973
+oid sha256:140d1156adb1988a2c0c257fa3688eaf1b602d5f6a2bd443857470ad6dc66eea
+size 2141773

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b5c63ff7594789af926646ac2065c922a80580f9c329df9531c50d54acfeae
-size 11653
+oid sha256:bd0bfcc6c960cd6d109baff9e4611bd22581776ba4cf9f04cf2ad2b9fdac58e0
+size 14609

results.json

@@ -1 +1 @@
-{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-25T01:40:23.944017"}
+{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-25T22:19:55.987410"}