{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4148443639278412, "min": 0.4148443639278412, "max": 1.4532759189605713, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12505.068359375, "min": 12505.068359375, "max": 44086.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29907.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29907.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5447947382926941, "min": -0.10040947794914246, "max": 0.5491938591003418, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.35609436035156, "min": -24.09827423095703, "max": 156.35609436035156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024888960644602776, "min": -0.0040784976445138454, "max": 0.3746778070926666, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.143131732940674, "min": -1.027781367301941, "max": 90.29734802246094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06949934788142507, "min": 0.06518967571254405, "max": 0.07414527335952568, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9729908703399511, "min": 0.507446215017672, "max": 1.0480933161161374, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018315707098476457, "min": 0.0007030853644446489, "max": 0.018315707098476457, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2564198993786704, "min": 0.009140109737780436, "max": 0.2564198993786704, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.361026117785714e-06, "min": 7.361026117785714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010305436564899999, "min": 0.00010305436564899999, "max": 0.0036336109887963996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245364285714287, "min": 0.10245364285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343510000000002, "min": 1.3886848, "max": 2.6112036, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002551189214285715, "min": 0.0002551189214285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035716649000000007, "min": 0.0035716649000000007, "max": 0.12113923964000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011891682632267475, "min": 0.01156805083155632, "max": 0.5108147859573364, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1664835512638092, "min": 0.1664835512638092, "max": 3.5757036209106445, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.9894736842105, "min": 328.9894736842105, "max": 990.2352941176471, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31254.0, "min": 16834.0, "max": 32272.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5867684057668636, "min": -0.9182545958143292, "max": 1.6037274786271154, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.74299854785204, "min": -30.302401661872864, "max": 150.74299854785204, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5867684057668636, "min": -0.9182545958143292, "max": 1.6037274786271154, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.74299854785204, "min": -30.302401661872864, "max": 150.74299854785204, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040232904318499525, "min": 0.040232904318499525, "max": 9.592037690036436, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.822125910257455, "min": 3.6039831908710767, "max": 163.06464073061943, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1793218881", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/cc/anaconda3/envs/unity-rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1793219850" }, "total": 968.9125110370005, "count": 1, "self": 0.21745906500109413, "children": { "run_training.setup": { "total": 0.01619942799970886, "count": 1, "self": 0.01619942799970886 }, "TrainerController.start_learning": { "total": 968.6788525439997, "count": 1, "self": 1.029774759238535, "children": { "TrainerController._reset_env": { "total": 1.708195414000329, "count": 1, "self": 1.708195414000329 }, "TrainerController.advance": { "total": 965.9044159117611, "count": 63793, "self": 0.9636000938071447, "children": { "env_step": { "total": 628.7271873039508, "count": 63793, "self": 512.2484924050232, "children": { "SubprocessEnvManager._take_step": { "total": 115.82252379402689, "count": 63793, "self": 2.8004627060026905, "children": { "TorchPolicy.evaluate": { "total": 113.0220610880242, "count": 62560, "self": 113.0220610880242 } } }, "workers": { "total": 0.6561711049007499, "count": 63793, "self": 0.0, "children": { "worker_root": { "total": 967.33673081098, "count": 63793, "is_parallel": true, "self": 516.2232633990161, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007296909998331103, "count": 1, "is_parallel": true, "self": 0.00022071199782658368, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005089790020065266, "count": 8, "is_parallel": true, "self": 0.0005089790020065266 } } }, "UnityEnvironment.step": { "total": 0.017433815999538638, "count": 1, "is_parallel": true, "self": 0.00019169699953636155, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001723790001051384, "count": 1, "is_parallel": true, "self": 0.0001723790001051384 }, "communicator.exchange": { "total": 0.01652810199993837, "count": 1, "is_parallel": true, "self": 0.01652810199993837 }, "steps_from_proto": { "total": 0.0005416379999587662, "count": 1, "is_parallel": true, "self": 0.00011194300077477237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004296949991839938, "count": 8, "is_parallel": true, "self": 0.0004296949991839938 } } } } } } }, "UnityEnvironment.step": { "total": 451.11346741196394, "count": 63792, "is_parallel": true, "self": 11.940126909877108, "children": { "UnityEnvironment._generate_step_input": { "total": 7.795907421927041, "count": 63792, "is_parallel": true, "self": 7.795907421927041 }, "communicator.exchange": { "total": 398.62214814012896, "count": 63792, "is_parallel": true, "self": 398.62214814012896 }, "steps_from_proto": { "total": 32.75528494003083, "count": 63792, "is_parallel": true, "self": 7.786643780232225, "children": { "_process_rank_one_or_two_observation": { "total": 24.968641159798608, "count": 510336, "is_parallel": true, "self": 24.968641159798608 } } } } } } } } } } }, "trainer_advance": { "total": 336.2136285140032, "count": 63793, "self": 1.803217079026581, "children": { "process_trajectory": { "total": 62.31726278097631, "count": 63793, "self": 62.223027026976524, "children": { "RLTrainer._checkpoint": { "total": 0.0942357539997829, "count": 2, "self": 0.0942357539997829 } } }, "_update_policy": { "total": 272.0931486540003, "count": 457, "self": 132.12896051889402, "children": { "TorchPPOOptimizer.update": { "total": 139.96418813510627, "count": 22800, "self": 139.96418813510627 } } } } } } }, "trainer_threads": { "total": 4.829998943023384e-07, "count": 1, "self": 4.829998943023384e-07 }, "TrainerController._save_models": { "total": 0.0364659759998176, "count": 1, "self": 0.0004310160002205521, "children": { "RLTrainer._checkpoint": { "total": 0.03603495999959705, "count": 1, "self": 0.03603495999959705 } } } } } } }