{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3154503107070923, "min": 0.3116927444934845, "max": 1.4364458322525024, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9453.4150390625, "min": 9415.6142578125, "max": 43576.01953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6557226777076721, "min": -0.13403336703777313, "max": 0.712612509727478, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 188.84812927246094, "min": -32.168006896972656, "max": 206.65762329101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017320821061730385, "min": 0.006019369699060917, "max": 0.31271132826805115, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.988396644592285, "min": 1.6493072509765625, "max": 74.32746887207031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07250089037374387, "min": 0.06522457755220655, "max": 0.07422000059326736, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.087513355606158, "min": 0.5103947816981302, "max": 1.0954654176020995, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016422002108690017, "min": 0.0006959711844059096, "max": 0.016422002108690017, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24633003163035028, "min": 0.007155220447495448, "max": 0.24633003163035028, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.555717481459999e-06, "min": 7.555717481459999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011333576222189998, "min": 0.00011333576222189998, "max": 0.0032529353156883004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251854, "min": 0.10251854, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377781000000001, "min": 1.3691136000000002, "max": 2.443222, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026160214599999995, "min": 0.00026160214599999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003924032189999999, "min": 0.003924032189999999, "max": 0.10845273883, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013091069646179676, "min": 0.013091069646179676, "max": 0.4626534581184387, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19636604189872742, "min": 0.18909674882888794, "max": 3.238574266433716, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 271.1509433962264, "min": 271.1509433962264, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28742.0, "min": 15984.0, "max": 32963.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6533603649937882, "min": -1.0000000521540642, "max": 1.7043110955920484, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.25619868934155, "min": -32.000001668930054, "max": 184.06559832394123, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6533603649937882, "min": -1.0000000521540642, "max": 1.7043110955920484, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.25619868934155, "min": -32.000001668930054, "max": 184.06559832394123, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03707709644059266, "min": 0.03707709644059266, "max": 8.98932876251638, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.930172222702822, "min": 3.930172222702822, "max": 143.82926020026207, "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": "1682420859", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682423191" }, "total": 2332.596419794, "count": 1, "self": 0.4905499179999424, "children": { "run_training.setup": { "total": 0.10533746800001609, "count": 1, "self": 0.10533746800001609 }, "TrainerController.start_learning": { "total": 2332.0005324080003, "count": 1, "self": 1.594152045982355, "children": { "TrainerController._reset_env": { "total": 3.763627880000058, "count": 1, "self": 3.763627880000058 }, "TrainerController.advance": { "total": 2326.548296368018, "count": 64204, "self": 1.644928222056933, "children": { "env_step": { "total": 1696.131329356011, "count": 64204, "self": 1579.3802473700387, "children": { "SubprocessEnvManager._take_step": { "total": 115.77721152793288, "count": 64204, "self": 5.103339184867082, "children": { "TorchPolicy.evaluate": { "total": 110.6738723430658, "count": 62557, "self": 110.6738723430658 } } }, "workers": { "total": 0.9738704580395279, "count": 64204, "self": 0.0, "children": { "worker_root": { "total": 2326.1430017410185, "count": 64204, "is_parallel": true, "self": 868.7792715900205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019039620001422008, "count": 1, "is_parallel": true, "self": 0.0005913710001550498, "children": { "_process_rank_one_or_two_observation": { "total": 0.001312590999987151, "count": 8, "is_parallel": true, "self": 0.001312590999987151 } } }, "UnityEnvironment.step": { "total": 0.05218460400010372, "count": 1, "is_parallel": true, "self": 0.0005369079999582027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005527840000922879, "count": 1, "is_parallel": true, "self": 0.0005527840000922879 }, "communicator.exchange": { "total": 0.04942254800016599, "count": 1, "is_parallel": true, "self": 0.04942254800016599 }, "steps_from_proto": { "total": 0.0016723639998872386, "count": 1, "is_parallel": true, "self": 0.0003786449997278396, "children": { "_process_rank_one_or_two_observation": { "total": 0.001293719000159399, "count": 8, "is_parallel": true, "self": 0.001293719000159399 } } } } } } }, "UnityEnvironment.step": { "total": 1457.363730150998, "count": 64203, "is_parallel": true, "self": 33.301917609003794, "children": { "UnityEnvironment._generate_step_input": { "total": 25.115730424002322, "count": 64203, "is_parallel": true, "self": 25.115730424002322 }, "communicator.exchange": { "total": 1297.1708794699587, "count": 64203, "is_parallel": true, "self": 1297.1708794699587 }, "steps_from_proto": { "total": 101.7752026480332, "count": 64203, "is_parallel": true, "self": 22.37716779604534, "children": { "_process_rank_one_or_two_observation": { "total": 79.39803485198786, "count": 513624, "is_parallel": true, "self": 79.39803485198786 } } } } } } } } } } }, "trainer_advance": { "total": 628.7720387899499, "count": 64204, "self": 2.8635847209359326, "children": { "process_trajectory": { "total": 114.28243313401208, "count": 64204, "self": 113.95241921201159, "children": { "RLTrainer._checkpoint": { "total": 0.3300139220004894, "count": 2, "self": 0.3300139220004894 } } }, "_update_policy": { "total": 511.62602093500186, "count": 445, "self": 327.60916656903805, "children": { "TorchPPOOptimizer.update": { "total": 184.0168543659638, "count": 22806, "self": 184.0168543659638 } } } } } } }, "trainer_threads": { "total": 1.0610001481836662e-06, "count": 1, "self": 1.0610001481836662e-06 }, "TrainerController._save_models": { "total": 0.0944550529998196, "count": 1, "self": 0.0014314259997263434, "children": { "RLTrainer._checkpoint": { "total": 0.09302362700009326, "count": 1, "self": 0.09302362700009326 } } } } } } }