Reinforce-PongPolGrad-1k training episodes

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 2000, "n_evaluation_episodes": 13, "max_t": 7000, "gamma": 0.96, "lr": 0.1, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3}
+{"h_size": 64, "n_training_episodes": 1000, "n_evaluation_episodes": 12, "max_t": 5500, "gamma": 0.98, "lr": 0.1, "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 sha256:24bd3b3a0ac23c708bc1685e2650a68c06d7a1ec7fc840493d2687fd045a5222
+oid sha256:5012782f05feb27d8830862e710a32718798cd67f19d11ba37fb080e5c08bd6e
 size 39511

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e6c3c64884fac3d4908e89f54ec08bceb6971e98fac6d0047ff6694ec23a10
-size 13525
+oid sha256:66a07c226bb903bd99769353153e5b4ded02ceaa8e7ab0d98c730b30ece38910
+size 18909

results.json

@@ -1 +1 @@
-{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 13, "eval_datetime": "2022-09-02T16:31:42.325801"}
+{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 12, "eval_datetime": "2022-09-02T22:02:08.331032"}