{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23453360795974731, "min": 0.1953631490468979, "max": 1.50232994556427, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 7054.77099609375, "min": 5920.28466796875, "max": 45574.6796875, "count": 66 }, "Pyramids.Step.mean": { "value": 1979915.0, "min": 29952.0, "max": 1979915.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979915.0, "min": 29952.0, "max": 1979915.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6958987712860107, "min": -0.1269349753856659, "max": 0.7781063914299011, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 204.59423828125, "min": -30.083589553833008, "max": 229.1328125, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01174519956111908, "min": -0.017928695306181908, "max": 0.2730512022972107, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.4530887603759766, "min": -5.002106189727783, "max": 65.53228759765625, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06838184033473399, "min": 0.06509955757064745, "max": 0.07357309589991091, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9573457646862759, "min": 0.4990568511320503, "max": 1.0883748224393153, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016964178403820068, "min": 0.0001750800621381293, "max": 0.018523617723904963, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23749849765348094, "min": 0.00245112086993381, "max": 0.2778542658585744, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.182523272524998e-06, "min": 5.182523272524998e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.255532581534997e-05, "min": 7.255532581534997e-05, "max": 0.0038541827652724494, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.101727475, "min": 0.101727475, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.42418465, "min": 1.3943424, "max": 2.68472755, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018257475249999997, "min": 0.00018257475249999997, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.0025560465349999993, "min": 0.0025560465349999993, "max": 0.128484282245, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007338341791182756, "min": 0.006963604129850864, "max": 0.3577478528022766, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10273678600788116, "min": 0.10009976476430893, "max": 2.504235029220581, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 272.32142857142856, "min": 238.89166666666668, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30500.0, "min": 15984.0, "max": 33984.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7273423266303432, "min": -1.0000000521540642, "max": 1.7437719170723045, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 191.7349982559681, "min": -31.99200163781643, "max": 212.2681984603405, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7273423266303432, "min": -1.0000000521540642, "max": 1.7437719170723045, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 191.7349982559681, "min": -31.99200163781643, "max": 212.2681984603405, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02087978300577405, "min": 0.01831468593421554, "max": 7.145384430885315, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3176559136409196, "min": 2.0752130590813067, "max": 114.32615089416504, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686640391", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686645201" }, "total": 4810.281842308999, "count": 1, "self": 0.47396022899920354, "children": { "run_training.setup": { "total": 0.03673959800016746, "count": 1, "self": 0.03673959800016746 }, "TrainerController.start_learning": { "total": 4809.771142482, "count": 1, "self": 2.9703759651001747, "children": { "TrainerController._reset_env": { "total": 4.93024182299996, "count": 1, "self": 4.93024182299996 }, "TrainerController.advance": { "total": 4801.778350416899, "count": 128943, "self": 2.938854371655907, "children": { "env_step": { "total": 3517.5195383514674, "count": 128943, "self": 3285.564847483598, "children": { "SubprocessEnvManager._take_step": { "total": 230.26380734010309, "count": 128943, "self": 9.927900544920703, "children": { "TorchPolicy.evaluate": { "total": 220.33590679518238, "count": 125059, "self": 220.33590679518238 } } }, "workers": { "total": 1.6908835277663457, "count": 128943, "self": 0.0, "children": { "worker_root": { "total": 4798.498668241822, "count": 128943, "is_parallel": true, "self": 1755.108176312635, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018128860001525027, "count": 1, "is_parallel": true, "self": 0.0005956989998594509, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012171870002930518, "count": 8, "is_parallel": true, "self": 0.0012171870002930518 } } }, "UnityEnvironment.step": { "total": 0.08455248000063875, "count": 1, "is_parallel": true, "self": 0.0006043680004950147, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004716359999292763, "count": 1, "is_parallel": true, "self": 0.0004716359999292763 }, "communicator.exchange": { "total": 0.08160083100028714, "count": 1, "is_parallel": true, "self": 0.08160083100028714 }, "steps_from_proto": { "total": 0.0018756449999273173, "count": 1, "is_parallel": true, "self": 0.00034731800042209215, "children": { "_process_rank_one_or_two_observation": { "total": 0.001528326999505225, "count": 8, "is_parallel": true, "self": 0.001528326999505225 } } } } } } }, "UnityEnvironment.step": { "total": 3043.390491929187, "count": 128942, "is_parallel": true, "self": 67.76356223221137, "children": { "UnityEnvironment._generate_step_input": { "total": 49.17509011002221, "count": 128942, "is_parallel": true, "self": 49.17509011002221 }, "communicator.exchange": { "total": 2709.1360837351376, "count": 128942, "is_parallel": true, "self": 2709.1360837351376 }, "steps_from_proto": { "total": 217.315755851816, "count": 128942, "is_parallel": true, "self": 43.748884456006635, "children": { "_process_rank_one_or_two_observation": { "total": 173.56687139580936, "count": 1031536, "is_parallel": true, "self": 173.56687139580936 } } } } } } } } } } }, "trainer_advance": { "total": 1281.319957693776, "count": 128943, "self": 5.784639683560272, "children": { "process_trajectory": { "total": 232.45521055223162, "count": 128943, "self": 231.99035041023035, "children": { "RLTrainer._checkpoint": { "total": 0.464860142001271, "count": 4, "self": 0.464860142001271 } } }, "_update_policy": { "total": 1043.080107457984, "count": 924, "self": 667.0150730828855, "children": { "TorchPPOOptimizer.update": { "total": 376.06503437509855, "count": 45585, "self": 376.06503437509855 } } } } } } }, "trainer_threads": { "total": 1.1880001693498343e-06, "count": 1, "self": 1.1880001693498343e-06 }, "TrainerController._save_models": { "total": 0.09217308900042553, "count": 1, "self": 0.0013682540011359379, "children": { "RLTrainer._checkpoint": { "total": 0.0908048349992896, "count": 1, "self": 0.0908048349992896 } } } } } } }