{"step": 0, "avg_reward": 0.4714483038156426} {"step": 7200, "avg_reward": 0.5663666518924791} {"step": 14400, "avg_reward": 0.569705726823096} {"step": 21600, "avg_reward": 0.5740199956743579} {"step": 28800, "avg_reward": 0.573887342033309} {"step": 36000, "avg_reward": 0.6045272605834595} {"step": 43200, "avg_reward": 0.5405997881724034} {"step": 50400, "avg_reward": 0.502069472695335} {"step": 57600, "avg_reward": 0.6652014100092596} {"step": 64800, "avg_reward": 0.5776967554685792} {"step": 72000, "avg_reward": 0.6279109552519263}