{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11416730284690857, "min": 0.09999330341815948, "max": 1.4370663166046143, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3392.138916015625, "min": 3022.197509765625, "max": 43594.84375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999965.0, "min": 29952.0, "max": 2999965.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999965.0, "min": 29952.0, "max": 2999965.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7158606052398682, "min": -0.12058256566524506, "max": 0.8633795380592346, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 208.3154296875, "min": -28.939815521240234, "max": 262.4673767089844, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01685119792819023, "min": -0.0061198631301522255, "max": 0.41500893235206604, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.903698444366455, "min": -1.7196815013885498, "max": 99.60214233398438, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06684000244075876, "min": 0.06372032736405907, "max": 0.07326416177175389, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9357600341706226, "min": 0.49722699010620913, "max": 1.067558757564756, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0164389403895863, "min": 0.0022369957929793028, "max": 0.0164389403895863, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2301451654542082, "min": 0.02162698981107402, "max": 0.2301451654542082, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5720066188880937e-06, "min": 1.5720066188880937e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2008092664433313e-05, "min": 2.2008092664433313e-05, "max": 0.0040275010574997, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052396904761905, "min": 0.10052396904761905, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073355666666667, "min": 1.3962282666666668, "max": 2.8425003, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.234450785714281e-05, "min": 6.234450785714281e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008728231099999995, "min": 0.0008728231099999995, "max": 0.13426577997, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007786952890455723, "min": 0.007475125137716532, "max": 0.5859311819076538, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10901734232902527, "min": 0.10465174913406372, "max": 4.101518154144287, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 226.43307086614172, "min": 206.22302158273382, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28757.0, "min": 15984.0, "max": 32924.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7263102207596845, "min": -1.0000000521540642, "max": 1.7801726490473575, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 219.24139803647995, "min": -30.73900167644024, "max": 247.4439982175827, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7263102207596845, "min": -1.0000000521540642, "max": 1.7801726490473575, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 219.24139803647995, "min": -30.73900167644024, "max": 247.4439982175827, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01850302251950493, "min": 0.01724014864916431, "max": 11.936820469796658, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.349883859977126, "min": 2.1525314017853816, "max": 190.98912751674652, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675444512", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675450817" }, "total": 6305.452113825, "count": 1, "self": 0.4421243759998106, "children": { "run_training.setup": { "total": 0.09560377599973435, "count": 1, "self": 0.09560377599973435 }, "TrainerController.start_learning": { "total": 6304.914385673001, "count": 1, "self": 3.3569577642811055, "children": { "TrainerController._reset_env": { "total": 5.906363309999961, "count": 1, "self": 5.906363309999961 }, "TrainerController.advance": { "total": 6295.570491149719, "count": 195404, "self": 3.5967888177447094, "children": { "env_step": { "total": 4410.330099498967, "count": 195404, "self": 4120.353593959512, "children": { "SubprocessEnvManager._take_step": { "total": 287.8603904921647, "count": 195404, "self": 11.950448158147537, "children": { "TorchPolicy.evaluate": { "total": 275.90994233401716, "count": 187559, "self": 93.59880413997507, "children": { "TorchPolicy.sample_actions": { "total": 182.3111381940421, "count": 187559, "self": 182.3111381940421 } } } } }, "workers": { "total": 2.1161150472898953, "count": 195404, "self": 0.0, "children": { "worker_root": { "total": 6295.616663750959, "count": 195404, "is_parallel": true, "self": 2446.795983927837, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017131109998445027, "count": 1, "is_parallel": true, "self": 0.0006448209996960941, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010682900001484086, "count": 8, "is_parallel": true, "self": 0.0010682900001484086 } } }, "UnityEnvironment.step": { "total": 0.04386745900001188, "count": 1, "is_parallel": true, "self": 0.0004476859999158478, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004063160004079691, "count": 1, "is_parallel": true, "self": 0.0004063160004079691 }, "communicator.exchange": { "total": 0.041496586999983265, "count": 1, "is_parallel": true, "self": 0.041496586999983265 }, "steps_from_proto": { "total": 0.0015168699997047952, "count": 1, "is_parallel": true, "self": 0.0003932599988729635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011236100008318317, "count": 8, "is_parallel": true, "self": 0.0011236100008318317 } } } } } } }, "UnityEnvironment.step": { "total": 3848.8206798231217, "count": 195403, "is_parallel": true, "self": 79.36524501332724, "children": { "UnityEnvironment._generate_step_input": { "total": 61.98703456679232, "count": 195403, "is_parallel": true, "self": 61.98703456679232 }, "communicator.exchange": { "total": 3429.956111836023, "count": 195403, "is_parallel": true, "self": 3429.956111836023 }, "steps_from_proto": { "total": 277.5122884069792, "count": 195403, "is_parallel": true, "self": 60.52417389829998, "children": { "_process_rank_one_or_two_observation": { "total": 216.98811450867925, "count": 1563224, "is_parallel": true, "self": 216.98811450867925 } } } } } } } } } } }, "trainer_advance": { "total": 1881.6436028330077, "count": 195404, "self": 6.598038349080525, "children": { "process_trajectory": { "total": 413.48598017291124, "count": 195404, "self": 412.9831428119119, "children": { "RLTrainer._checkpoint": { "total": 0.502837360999365, "count": 6, "self": 0.502837360999365 } } }, "_update_policy": { "total": 1461.559584311016, "count": 1402, "self": 553.5056703099535, "children": { "TorchPPOOptimizer.update": { "total": 908.0539140010624, "count": 68397, "self": 908.0539140010624 } } } } } } }, "trainer_threads": { "total": 9.57999873207882e-07, "count": 1, "self": 9.57999873207882e-07 }, "TrainerController._save_models": { "total": 0.08057249100056652, "count": 1, "self": 0.0013065230014035478, "children": { "RLTrainer._checkpoint": { "total": 0.07926596799916297, "count": 1, "self": 0.07926596799916297 } } } } } } }