{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2330177128314972, "min": 0.2330177128314972, "max": 1.5512512922286987, "count": 68 }, "Pyramids.Policy.Entropy.sum": { "value": 6964.43359375, "min": 6964.43359375, "max": 47058.7578125, "count": 68 }, "Pyramids.Step.mean": { "value": 2039894.0, "min": 29952.0, "max": 2039894.0, "count": 68 }, "Pyramids.Step.sum": { "value": 2039894.0, "min": 29952.0, "max": 2039894.0, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6805641651153564, "min": -0.12414652854204178, "max": 0.7525332570075989, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 194.641357421875, "min": -29.795166015625, "max": 220.49224853515625, "count": 68 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019790425896644592, "min": -0.0011523724533617496, "max": 0.5536867380142212, "count": 68 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.660061836242676, "min": -0.285788357257843, "max": 131.2237548828125, "count": 68 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06615853581320087, "min": 0.06239686218068833, "max": 0.07503146900815112, "count": 68 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9262195013848122, "min": 0.48613608605797065, "max": 1.1066972581480228, "count": 68 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011956495561093062, "min": 0.00043928236265134633, "max": 0.014656954068816577, "count": 68 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16739093785530287, "min": 0.003074976538559424, "max": 0.215170973877927, "count": 68 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.755724605236905e-05, "min": 9.755724605236905e-05, "max": 0.00029838354339596195, "count": 68 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0013658014447331666, "min": 0.0013658014447331666, "max": 0.003969015376994899, "count": 68 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13251905952380955, "min": 0.13251905952380955, "max": 0.19946118095238097, "count": 68 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8552668333333335, "min": 1.3757013333333334, "max": 2.7374533000000003, "count": 68 }, "Pyramids.Policy.Beta.mean": { "value": 0.0032586540464285716, "min": 0.0032586540464285716, "max": 0.009946171977142856, "count": 68 }, "Pyramids.Policy.Beta.sum": { "value": 0.04562115665, "min": 0.04562115665, "max": 0.13230820949000002, "count": 68 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004568756558001041, "min": 0.004568756558001041, "max": 0.36913421750068665, "count": 68 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06396259367465973, "min": 0.06396259367465973, "max": 2.583939552307129, "count": 68 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.95283018867923, "min": 271.7567567567568, "max": 999.0, "count": 68 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31795.0, "min": 15984.0, "max": 33439.0, "count": 68 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6450373704466865, "min": -1.0000000521540642, "max": 1.7113711185676534, "count": 68 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.01899863779545, "min": -32.000001668930054, "max": 188.01859804987907, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6450373704466865, "min": -1.0000000521540642, "max": 1.7113711185676534, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.01899863779545, "min": -32.000001668930054, "max": 188.01859804987907, "count": 68 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014316193433859273, "min": 0.01361969543676506, "max": 7.536140745505691, "count": 68 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5318326974229421, "min": 1.3693665615282953, "max": 120.57825192809105, "count": 68 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704550582", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704555306" }, "total": 4724.239417803, "count": 1, "self": 0.773212393999529, "children": { "run_training.setup": { "total": 0.052989432000003944, "count": 1, "self": 0.052989432000003944 }, "TrainerController.start_learning": { "total": 4723.413215977001, "count": 1, "self": 3.0437041291388596, "children": { "TrainerController._reset_env": { "total": 3.800391533000038, "count": 1, "self": 3.800391533000038 }, "TrainerController.advance": { "total": 4716.394457441862, "count": 131675, "self": 3.095794261955234, "children": { "env_step": { "total": 3376.7390581370782, "count": 131675, "self": 3101.5926492621015, "children": { "SubprocessEnvManager._take_step": { "total": 273.3280973479481, "count": 131675, "self": 10.053644099019493, "children": { "TorchPolicy.evaluate": { "total": 263.2744532489286, "count": 128232, "self": 263.2744532489286 } } }, "workers": { "total": 1.818311527028527, "count": 131675, "self": 0.0, "children": { "worker_root": { "total": 4711.869233105034, "count": 131675, "is_parallel": true, "self": 1863.936440574972, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0039018779999651088, "count": 1, "is_parallel": true, "self": 0.0027550999999448322, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011467780000202765, "count": 8, "is_parallel": true, "self": 0.0011467780000202765 } } }, "UnityEnvironment.step": { "total": 0.0823522859999457, "count": 1, "is_parallel": true, "self": 0.0006416300000182673, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005244599999514321, "count": 1, "is_parallel": true, "self": 0.0005244599999514321 }, "communicator.exchange": { "total": 0.07933476699997755, "count": 1, "is_parallel": true, "self": 0.07933476699997755 }, "steps_from_proto": { "total": 0.0018514289999984612, "count": 1, "is_parallel": true, "self": 0.0003998850000925813, "children": { "_process_rank_one_or_two_observation": { "total": 0.00145154399990588, "count": 8, "is_parallel": true, "self": 0.00145154399990588 } } } } } } }, "UnityEnvironment.step": { "total": 2847.932792530062, "count": 131674, "is_parallel": true, "self": 75.42222613039667, "children": { "UnityEnvironment._generate_step_input": { "total": 51.01209129894585, "count": 131674, "is_parallel": true, "self": 51.01209129894585 }, "communicator.exchange": { "total": 2509.1681420298337, "count": 131674, "is_parallel": true, "self": 2509.1681420298337 }, "steps_from_proto": { "total": 212.3303330708859, "count": 131674, "is_parallel": true, "self": 42.927148922235574, "children": { "_process_rank_one_or_two_observation": { "total": 169.40318414865033, "count": 1053392, "is_parallel": true, "self": 169.40318414865033 } } } } } } } } } } }, "trainer_advance": { "total": 1336.5596050428283, "count": 131675, "self": 5.902707291743809, "children": { "process_trajectory": { "total": 269.95778163809155, "count": 131675, "self": 269.58117030009157, "children": { "RLTrainer._checkpoint": { "total": 0.37661133799997515, "count": 4, "self": 0.37661133799997515 } } }, "_update_policy": { "total": 1060.699116112993, "count": 936, "self": 629.559274961939, "children": { "TorchPPOOptimizer.update": { "total": 431.13984115105393, "count": 46765, "self": 431.13984115105393 } } } } } } }, "trainer_threads": { "total": 1.1610000001383014e-06, "count": 1, "self": 1.1610000001383014e-06 }, "TrainerController._save_models": { "total": 0.17466171199976088, "count": 1, "self": 0.0020275679999031126, "children": { "RLTrainer._checkpoint": { "total": 0.17263414399985777, "count": 1, "self": 0.17263414399985777 } } } } } } }