{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20136667788028717, "min": 0.19703738391399384, "max": 1.6038053035736084, "count": 300 }, "Pyramids.Policy.Entropy.sum": { "value": 1978.2261962890625, "min": 1799.8167724609375, "max": 25660.884765625, "count": 300 }, "Pyramids.Step.mean": { "value": 2999928.0, "min": 9656.0, "max": 2999928.0, "count": 300 }, "Pyramids.Step.sum": { "value": 2999928.0, "min": 9656.0, "max": 2999928.0, "count": 300 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8044412136077881, "min": -0.10177898406982422, "max": 0.8239906430244446, "count": 300 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 41.8309440612793, "min": -2.077310562133789, "max": 46.00168228149414, "count": 300 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011080126278102398, "min": -0.03499497100710869, "max": 0.4802721440792084, "count": 300 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.576166570186615, "min": -1.4769809246063232, "max": 9.605443000793457, "count": 300 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04731362007320664, "min": 0.03871807591349352, "max": 0.060168491637644664, "count": 300 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.14194086021961994, "min": 0.04335498666902519, "max": 0.1666318783693486, "count": 300 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01587104935768164, "min": 0.00011333386328187302, "max": 0.01914441247765139, "count": 300 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04761314807304492, "min": 0.0001595930973508075, "max": 0.05543504082985844, "count": 300 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.718998094000001e-07, "min": 5.718998094000001e-07, "max": 0.00029918080027306664, "count": 300 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.7156994282000003e-06, "min": 1.7156994282000003e-06, "max": 0.0008023654325448667, "count": 300 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1001906, "min": 0.1001906, "max": 0.19972693333333336, "count": 300 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.3005718, "min": 0.1917991999999999, "max": 0.5674551333333334, "count": 300 }, "Pyramids.Policy.Beta.mean": { "value": 2.904094e-05, "min": 2.904094e-05, "max": 0.00997272064, "count": 300 }, "Pyramids.Policy.Beta.sum": { "value": 8.712282e-05, "min": 8.712282e-05, "max": 0.026748767819999998, "count": 300 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0068595088087022305, "min": 0.006644914858043194, "max": 0.8820486068725586, "count": 300 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.020578525960445404, "min": 0.013289829716086388, "max": 0.8820486068725586, "count": 300 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 209.44230769230768, "min": 178.10714285714286, "max": 999.0, "count": 294 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 10891.0, "min": 658.0, "max": 16172.0, "count": 294 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7900384412362025, "min": -1.0000000596046448, "max": 1.8226071234260286, "count": 300 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.08199894428253, "min": -15.99760091304779, "max": 102.0659989118576, "count": 300 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7900384412362025, "min": -1.0000000596046448, "max": 1.8226071234260286, "count": 300 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.08199894428253, "min": -15.99760091304779, "max": 102.0659989118576, "count": 300 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014981254868101902, "min": 0.012544478326305454, "max": 11.339652299880981, "count": 300 }, "Pyramids.Policy.RndReward.sum": { "value": 0.7790252531412989, "min": 0.605669315205887, "max": 139.82518529891968, "count": 300 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 300 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 300 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1746221885", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/hiyo2044/Project/learn2/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training3 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1746226316" }, "total": 4430.871955030998, "count": 1, "self": 0.2681569260021206, "children": { "run_training.setup": { "total": 0.017494758998509496, "count": 1, "self": 0.017494758998509496 }, "TrainerController.start_learning": { "total": 4430.586303345997, "count": 1, "self": 2.184868701704545, "children": { "TrainerController._reset_env": { "total": 2.6924219369975617, "count": 1, "self": 2.6924219369975617 }, "TrainerController.advance": { "total": 4425.641008509294, "count": 195214, "self": 2.0052785059888265, "children": { "env_step": { "total": 3366.7808854594914, "count": 195214, "self": 2810.775812443586, "children": { "SubprocessEnvManager._take_step": { "total": 554.5349331148536, "count": 195214, "self": 6.2706119196882355, "children": { "TorchPolicy.evaluate": { "total": 548.2643211951654, "count": 187589, "self": 548.2643211951654 } } }, "workers": { "total": 1.4701399010518799, "count": 195214, "self": 0.0, "children": { "worker_root": { "total": 4423.837233968799, "count": 195214, "is_parallel": true, "self": 1761.1734096485743, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018415559970890172, "count": 1, "is_parallel": true, "self": 0.00092751099873567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009140449983533472, "count": 8, "is_parallel": true, "self": 0.0009140449983533472 } } }, "UnityEnvironment.step": { "total": 0.029260734998388216, "count": 1, "is_parallel": true, "self": 0.00018713199824560434, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021010199998272583, "count": 1, "is_parallel": true, "self": 0.00021010199998272583 }, "communicator.exchange": { "total": 0.028327128995442763, "count": 1, "is_parallel": true, "self": 0.028327128995442763 }, "steps_from_proto": { "total": 0.0005363720047171228, "count": 1, "is_parallel": true, "self": 0.00012561601033667102, "children": { "_process_rank_one_or_two_observation": { "total": 0.00041075599438045174, "count": 8, "is_parallel": true, "self": 0.00041075599438045174 } } } } } } }, "UnityEnvironment.step": { "total": 2662.663824320225, "count": 195213, "is_parallel": true, "self": 30.67984672971943, "children": { "UnityEnvironment._generate_step_input": { "total": 22.02629085243825, "count": 195213, "is_parallel": true, "self": 22.02629085243825 }, "communicator.exchange": { "total": 2520.834833553068, "count": 195213, "is_parallel": true, "self": 2520.834833553068 }, "steps_from_proto": { "total": 89.12285318499926, "count": 195213, "is_parallel": true, "self": 19.877482604963006, "children": { "_process_rank_one_or_two_observation": { "total": 69.24537058003625, "count": 1561704, "is_parallel": true, "self": 69.24537058003625 } } } } } } } } } } }, "trainer_advance": { "total": 1056.8548445438137, "count": 195214, "self": 4.822267885669135, "children": { "process_trajectory": { "total": 193.50502791818872, "count": 195214, "self": 193.05120097518375, "children": { "RLTrainer._checkpoint": { "total": 0.4538269430049695, "count": 6, "self": 0.4538269430049695 } } }, "_update_policy": { "total": 858.5275487399558, "count": 673, "self": 411.2859345053803, "children": { "TorchPPOOptimizer.update": { "total": 447.24161423457554, "count": 34608, "self": 447.24161423457554 } } } } } } }, "trainer_threads": { "total": 6.310001481324434e-07, "count": 1, "self": 6.310001481324434e-07 }, "TrainerController._save_models": { "total": 0.06800356700114207, "count": 1, "self": 0.0010422109990031458, "children": { "RLTrainer._checkpoint": { "total": 0.06696135600213893, "count": 1, "self": 0.06696135600213893 } } } } } } }