{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31247687339782715, "min": 0.30705997347831726, "max": 1.5331116914749146, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 9449.30078125, "min": 9241.27734375, "max": 49059.57421875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999929.0, "min": 29912.0, "max": 2999929.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999929.0, "min": 29912.0, "max": 2999929.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8012208938598633, "min": -0.08035261183977127, "max": 0.8571059107780457, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.62342834472656, "min": -9.722665786743164, "max": 161.1359100341797, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01914004608988762, "min": 0.003724323818460107, "max": 0.7179870009422302, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.5026283264160156, "min": 0.6592053174972534, "max": 86.15843963623047, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.05207956740854397, "min": 0.04436287736254079, "max": 0.05367412116123866, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3645569718598078, "min": 0.15882645718197133, "max": 0.4018988498525383, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01624666669661002, "min": 0.0009054124150600877, "max": 0.02311014503809727, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11372666687627013, "min": 0.006337886905420614, "max": 0.1348958711217468, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.3898281081857136e-06, "min": 1.3898281081857136e-06, "max": 0.0002983872005376, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 9.728796757299994e-06, "min": 9.728796757299994e-06, "max": 0.002005063431645533, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10046324285714285, "min": 0.10046324285714285, "max": 0.19946240000000004, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7032427, "min": 0.5983872000000001, "max": 1.4361009666666666, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001026022471428571, "min": 0.0001026022471428571, "max": 0.01989253376, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0007182157299999997, "min": 0.0007182157299999997, "max": 0.13367405788666667, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010210190899670124, "min": 0.01020765770226717, "max": 0.721411406993866, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07147133350372314, "min": 0.07145360112190247, "max": 2.164234161376953, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 212.51724137931035, "min": 196.09677419354838, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30815.0, "min": 15901.0, "max": 33097.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7790513676073816, "min": -1.0000000596046448, "max": 1.80387010647879, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 256.18339693546295, "min": -30.418201863765717, "max": 277.7959963977337, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7790513676073816, "min": -1.0000000596046448, "max": 1.80387010647879, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 256.18339693546295, "min": -30.418201863765717, "max": 277.7959963977337, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032515130887683576, "min": 0.0317843025848844, "max": 16.12166660764943, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 4.682178847826435, "min": 4.674770064186305, "max": 370.7983319759369, "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": "1699505183", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1699512630" }, "total": 7446.740678169999, "count": 1, "self": 1.493672078999225, "children": { "run_training.setup": { "total": 0.045590855000000374, "count": 1, "self": 0.045590855000000374 }, "TrainerController.start_learning": { "total": 7445.201415236, "count": 1, "self": 4.40899865665142, "children": { "TrainerController._reset_env": { "total": 8.770678235999867, "count": 1, "self": 8.770678235999867 }, "TrainerController.advance": { "total": 7431.898521112347, "count": 195645, "self": 4.798092234344949, "children": { "env_step": { "total": 5711.438486441023, "count": 195645, "self": 5300.082846881958, "children": { "SubprocessEnvManager._take_step": { "total": 408.5405807408147, "count": 195645, "self": 14.703647576610138, "children": { "TorchPolicy.evaluate": { "total": 393.83693316420454, "count": 187607, "self": 393.83693316420454 } } }, "workers": { "total": 2.815058818250236, "count": 195645, "self": 0.0, "children": { "worker_root": { "total": 7430.293609286816, "count": 195645, "is_parallel": true, "self": 2495.0359958700756, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004553407999992487, "count": 1, "is_parallel": true, "self": 0.001244131000021298, "children": { "_process_rank_one_or_two_observation": { "total": 0.003309276999971189, "count": 8, "is_parallel": true, "self": 0.003309276999971189 } } }, "UnityEnvironment.step": { "total": 0.044121609000058015, "count": 1, "is_parallel": true, "self": 0.0005865109997102991, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004909460001272237, "count": 1, "is_parallel": true, "self": 0.0004909460001272237 }, "communicator.exchange": { "total": 0.041276623000158, "count": 1, "is_parallel": true, "self": 0.041276623000158 }, "steps_from_proto": { "total": 0.0017675290000624955, "count": 1, "is_parallel": true, "self": 0.00037739399976999266, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013901350002925028, "count": 8, "is_parallel": true, "self": 0.0013901350002925028 } } } } } } }, "UnityEnvironment.step": { "total": 4935.25761341674, "count": 195644, "is_parallel": true, "self": 108.27818516954085, "children": { "UnityEnvironment._generate_step_input": { "total": 74.22458375502879, "count": 195644, "is_parallel": true, "self": 74.22458375502879 }, "communicator.exchange": { "total": 4418.108110362935, "count": 195644, "is_parallel": true, "self": 4418.108110362935 }, "steps_from_proto": { "total": 334.6467341292355, "count": 195644, "is_parallel": true, "self": 67.4782168374179, "children": { "_process_rank_one_or_two_observation": { "total": 267.1685172918176, "count": 1565152, "is_parallel": true, "self": 267.1685172918176 } } } } } } } } } } }, "trainer_advance": { "total": 1715.6619424369794, "count": 195645, "self": 9.332942809893893, "children": { "process_trajectory": { "total": 342.0145541620957, "count": 195645, "self": 341.4315822300957, "children": { "RLTrainer._checkpoint": { "total": 0.582971931999964, "count": 6, "self": 0.582971931999964 } } }, "_update_policy": { "total": 1364.3144454649898, "count": 702, "self": 1016.7896614480603, "children": { "TorchPPOOptimizer.update": { "total": 347.5247840169295, "count": 34269, "self": 347.5247840169295 } } } } } } }, "trainer_threads": { "total": 1.263000740436837e-06, "count": 1, "self": 1.263000740436837e-06 }, "TrainerController._save_models": { "total": 0.1232159680002951, "count": 1, "self": 0.0020980760018574074, "children": { "RLTrainer._checkpoint": { "total": 0.1211178919984377, "count": 1, "self": 0.1211178919984377 } } } } } } }