{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4934672713279724, "min": 0.4934672713279724, "max": 1.4450116157531738, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14732.958984375, "min": 14732.958984375, "max": 43835.87109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29874.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29874.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27884921431541443, "min": -0.17593970894813538, "max": 0.28898894786834717, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.94309997558594, "min": -41.69771194458008, "max": 75.42611694335938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.056208305060863495, "min": -0.030473720282316208, "max": 0.2238595336675644, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.501742362976074, "min": -7.9231672286987305, "max": 53.054710388183594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07014219388042368, "min": 0.0658704014723688, "max": 0.07354745060162741, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0521329082063553, "min": 0.5776908353363143, "max": 1.0521329082063553, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014194753618438779, "min": 0.0001860607926464386, "max": 0.014194753618438779, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21292130427658168, "min": 0.0026048510970501405, "max": 0.21292130427658168, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4775575075133285e-06, "min": 7.4775575075133285e-06, "max": 0.000294848776717075, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011216336261269993, "min": 0.00011216336261269993, "max": 0.003507914630695199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249248666666669, "min": 0.10249248666666669, "max": 0.198282925, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373873000000002, "min": 1.4780293000000002, "max": 2.5693048000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002589994179999999, "min": 0.0002589994179999999, "max": 0.0098284642075, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003884991269999998, "min": 0.003884991269999998, "max": 0.11695354952, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010413600131869316, "min": 0.010413600131869316, "max": 0.2825762927532196, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1562040001153946, "min": 0.1539803445339203, "max": 2.260610342025757, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 538.4561403508771, "min": 538.4561403508771, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30692.0, "min": 16417.0, "max": 33253.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0754561109239595, "min": -0.999987552408129, "max": 1.1025499586875622, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 61.30099832266569, "min": -31.999601677060127, "max": 61.30099832266569, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0754561109239595, "min": -0.999987552408129, "max": 1.1025499586875622, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 61.30099832266569, "min": -31.999601677060127, "max": 61.30099832266569, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.058395058635556905, "min": 0.058395058635556905, "max": 5.646892654106898, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3285183422267437, "min": 3.279166377404181, "max": 95.99717511981726, "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": "1690883048", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690885344" }, "total": 2296.321596244, "count": 1, "self": 0.5306272090001585, "children": { "run_training.setup": { "total": 0.04446796100000938, "count": 1, "self": 0.04446796100000938 }, "TrainerController.start_learning": { "total": 2295.7465010739998, "count": 1, "self": 1.46235737793495, "children": { "TrainerController._reset_env": { "total": 4.248992591999922, "count": 1, "self": 4.248992591999922 }, "TrainerController.advance": { "total": 2289.932577652064, "count": 63405, "self": 1.4369880831704904, "children": { "env_step": { "total": 1589.1509158689992, "count": 63405, "self": 1474.3315427470602, "children": { "SubprocessEnvManager._take_step": { "total": 113.94385847899184, "count": 63405, "self": 4.8541462100729404, "children": { "TorchPolicy.evaluate": { "total": 109.0897122689189, "count": 62577, "self": 109.0897122689189 } } }, "workers": { "total": 0.8755146429471097, "count": 63405, "self": 0.0, "children": { "worker_root": { "total": 2290.266117599915, "count": 63405, "is_parallel": true, "self": 936.3116937949021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00179847300023539, "count": 1, "is_parallel": true, "self": 0.0005892199997106218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012092530005247681, "count": 8, "is_parallel": true, "self": 0.0012092530005247681 } } }, "UnityEnvironment.step": { "total": 0.05288322300020809, "count": 1, "is_parallel": true, "self": 0.0005624289997285814, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005639020000671735, "count": 1, "is_parallel": true, "self": 0.0005639020000671735 }, "communicator.exchange": { "total": 0.04986806000033539, "count": 1, "is_parallel": true, "self": 0.04986806000033539 }, "steps_from_proto": { "total": 0.0018888320000769454, "count": 1, "is_parallel": true, "self": 0.000369254999441182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015195770006357634, "count": 8, "is_parallel": true, "self": 0.0015195770006357634 } } } } } } }, "UnityEnvironment.step": { "total": 1353.954423805013, "count": 63404, "is_parallel": true, "self": 36.29273797097221, "children": { "UnityEnvironment._generate_step_input": { "total": 24.630590313025095, "count": 63404, "is_parallel": true, "self": 24.630590313025095 }, "communicator.exchange": { "total": 1186.0272770850838, "count": 63404, "is_parallel": true, "self": 1186.0272770850838 }, "steps_from_proto": { "total": 107.00381843593186, "count": 63404, "is_parallel": true, "self": 21.555862068659735, "children": { "_process_rank_one_or_two_observation": { "total": 85.44795636727213, "count": 507232, "is_parallel": true, "self": 85.44795636727213 } } } } } } } } } } }, "trainer_advance": { "total": 699.3446736998944, "count": 63405, "self": 2.6815816988696497, "children": { "process_trajectory": { "total": 112.92814549203467, "count": 63405, "self": 112.71062610503486, "children": { "RLTrainer._checkpoint": { "total": 0.2175193869998111, "count": 2, "self": 0.2175193869998111 } } }, "_update_policy": { "total": 583.7349465089901, "count": 449, "self": 382.42100187805863, "children": { "TorchPPOOptimizer.update": { "total": 201.31394463093147, "count": 22764, "self": 201.31394463093147 } } } } } } }, "trainer_threads": { "total": 9.380000847158954e-07, "count": 1, "self": 9.380000847158954e-07 }, "TrainerController._save_models": { "total": 0.10257251400071254, "count": 1, "self": 0.001436692000424955, "children": { "RLTrainer._checkpoint": { "total": 0.10113582200028759, "count": 1, "self": 0.10113582200028759 } } } } } } }