{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17339228093624115, "min": 0.1673576682806015, "max": 1.4537467956542969, "count": 78 }, "Pyramids.Policy.Entropy.sum": { "value": 5232.28564453125, "min": 4937.720703125, "max": 44100.86328125, "count": 78 }, "Pyramids.Step.mean": { "value": 2339978.0, "min": 29952.0, "max": 2339978.0, "count": 78 }, "Pyramids.Step.sum": { "value": 2339978.0, "min": 29952.0, "max": 2339978.0, "count": 78 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8033431768417358, "min": -0.09590227901935577, "max": 0.8676595687866211, "count": 78 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 239.39627075195312, "min": -23.112449645996094, "max": 261.16552734375, "count": 78 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.016224941238760948, "min": -0.026987379416823387, "max": 0.2857888340950012, "count": 78 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.8350324630737305, "min": -7.961277008056641, "max": 67.7319564819336, "count": 78 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06866516700358175, "min": 0.0639966518772001, "max": 0.07612412786138953, "count": 78 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9613123380501444, "min": 0.4537449659366192, "max": 1.0939651658203837, "count": 78 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012922226129116355, "min": 0.0009945667884971557, "max": 0.016702198276540174, "count": 78 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18091116580762898, "min": 0.008370588159595039, "max": 0.24216407784842886, "count": 78 }, "Pyramids.Policy.LearningRate.mean": { "value": 6.74844417909262e-05, "min": 6.74844417909262e-05, "max": 0.00029838354339596195, "count": 78 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009447821850729667, "min": 0.0009447821850729667, "max": 0.003982469272510299, "count": 78 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1224947880952381, "min": 0.1224947880952381, "max": 0.19946118095238097, "count": 78 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.7149270333333335, "min": 1.3897045333333333, "max": 2.8274897, "count": 78 }, "Pyramids.Policy.Beta.mean": { "value": 0.0022572293307142857, "min": 0.0022572293307142857, "max": 0.009946171977142856, "count": 78 }, "Pyramids.Policy.Beta.sum": { "value": 0.03160121063, "min": 0.03160121063, "max": 0.13276622103, "count": 78 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008497459813952446, "min": 0.008410836569964886, "max": 0.3895607590675354, "count": 78 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11896443367004395, "min": 0.11775171756744385, "max": 2.7269253730773926, "count": 78 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 223.6793893129771, "min": 210.8368794326241, "max": 999.0, "count": 78 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29302.0, "min": 15984.0, "max": 33288.0, "count": 78 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7152442631830696, "min": -1.0000000521540642, "max": 1.789091534597773, "count": 78 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 224.69699847698212, "min": -32.000001668930054, "max": 254.05099791288376, "count": 78 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7152442631830696, "min": -1.0000000521540642, "max": 1.789091534597773, "count": 78 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 224.69699847698212, "min": -32.000001668930054, "max": 254.05099791288376, "count": 78 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019972447125907216, "min": 0.019972447125907216, "max": 7.869988411664963, "count": 78 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6163905734938453, "min": 2.6163905734938453, "max": 125.9198145866394, "count": 78 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 78 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 78 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684603522", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1684609159" }, "total": 5636.650886999, "count": 1, "self": 0.324848842999927, "children": { "run_training.setup": { "total": 0.038247275000003356, "count": 1, "self": 0.038247275000003356 }, "TrainerController.start_learning": { "total": 5636.287790881001, "count": 1, "self": 3.1631559099614606, "children": { "TrainerController._reset_env": { "total": 3.830480279000085, "count": 1, "self": 3.830480279000085 }, "TrainerController.advance": { "total": 5629.127078847039, "count": 152208, "self": 3.1663169581061084, "children": { "env_step": { "total": 4133.278663468927, "count": 152208, "self": 3880.6826167147083, "children": { "SubprocessEnvManager._take_step": { "total": 250.68745014010506, "count": 152208, "self": 10.876485244204332, "children": { "TorchPolicy.evaluate": { "total": 239.81096489590072, "count": 146668, "self": 239.81096489590072 } } }, "workers": { "total": 1.9085966141142308, "count": 152207, "self": 0.0, "children": { "worker_root": { "total": 5624.274150821867, "count": 152207, "is_parallel": true, "self": 2009.3298120629042, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017942099998435879, "count": 1, "is_parallel": true, "self": 0.0005769829995188047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012172270003247831, "count": 8, "is_parallel": true, "self": 0.0012172270003247831 } } }, "UnityEnvironment.step": { "total": 0.05563300700009677, "count": 1, "is_parallel": true, "self": 0.0005349190000742965, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005309800001214171, "count": 1, "is_parallel": true, "self": 0.0005309800001214171 }, "communicator.exchange": { "total": 0.052541047999966395, "count": 1, "is_parallel": true, "self": 0.052541047999966395 }, "steps_from_proto": { "total": 0.0020260599999346596, "count": 1, "is_parallel": true, "self": 0.0003907450000042445, "children": { "_process_rank_one_or_two_observation": { "total": 0.001635314999930415, "count": 8, "is_parallel": true, "self": 0.001635314999930415 } } } } } } }, "UnityEnvironment.step": { "total": 3614.9443387589627, "count": 152206, "is_parallel": true, "self": 74.46193473302674, "children": { "UnityEnvironment._generate_step_input": { "total": 54.07019435497932, "count": 152206, "is_parallel": true, "self": 54.07019435497932 }, "communicator.exchange": { "total": 3254.651392466947, "count": 152206, "is_parallel": true, "self": 3254.651392466947 }, "steps_from_proto": { "total": 231.76081720400953, "count": 152206, "is_parallel": true, "self": 47.01802883591358, "children": { "_process_rank_one_or_two_observation": { "total": 184.74278836809594, "count": 1217648, "is_parallel": true, "self": 184.74278836809594 } } } } } } } } } } }, "trainer_advance": { "total": 1492.682098420006, "count": 152207, "self": 6.486253035062418, "children": { "process_trajectory": { "total": 259.27157443392866, "count": 152207, "self": 258.8840111799284, "children": { "RLTrainer._checkpoint": { "total": 0.3875632540002698, "count": 4, "self": 0.3875632540002698 } } }, "_update_policy": { "total": 1226.924270951015, "count": 1085, "self": 789.7252650120129, "children": { "TorchPPOOptimizer.update": { "total": 437.19900593900206, "count": 53463, "self": 437.19900593900206 } } } } } } }, "trainer_threads": { "total": 1.4799998098169453e-06, "count": 1, "self": 1.4799998098169453e-06 }, "TrainerController._save_models": { "total": 0.16707436500018957, "count": 1, "self": 0.0019503429994074395, "children": { "RLTrainer._checkpoint": { "total": 0.16512402200078213, "count": 1, "self": 0.16512402200078213 } } } } } } }