MattStammers
/

appo-atari_berzerk-superhuman

Reinforcement Learning

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

MattStammers commited on Oct 26, 2023

Commit

f5a91a5

·

1 Parent(s): 56530ba

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -110,7 +110,7 @@ hyperparameters =  {
   "summaries_use_frameskip": true,
   "heartbeat_interval": 10,
   "heartbeat_reporting_interval": 60,
-  "train_for_env_steps": 100000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

   "summaries_use_frameskip": true,
   "heartbeat_interval": 10,
   "heartbeat_reporting_interval": 60,
+  "train_for_env_steps": 500000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,