{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17308558523654938, "min": 0.16564275324344635, "max": 1.4798009395599365, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5153.79638671875, "min": 4900.375, "max": 44891.2421875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999917.0, "min": 29952.0, "max": 2999917.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999917.0, "min": 29952.0, "max": 2999917.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7402231097221375, "min": -0.14191217720508575, "max": 0.8177164196968079, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 222.06692504882812, "min": -33.63318634033203, "max": 242.0440673828125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008856922388076782, "min": -0.04643089696764946, "max": 0.31520694494247437, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.657076835632324, "min": -13.093512535095215, "max": 74.70404815673828, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06818359843019922, "min": 0.06392046118326973, "max": 0.07416387771358823, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9545703780227891, "min": 0.4954628263591473, "max": 1.0549423492384626, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015026730969835188, "min": 0.0009517076348927487, "max": 0.016312709568453664, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21037423357769264, "min": 0.013323906888498481, "max": 0.2327484996446098, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.516599494500005e-06, "min": 1.516599494500005e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1232392923000068e-05, "min": 2.1232392923000068e-05, "max": 0.004117587127470999, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1005055, "min": 0.1005055, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.407077, "min": 1.3962282666666668, "max": 2.8725290000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.049945000000016e-05, "min": 6.049945000000016e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008469923000000022, "min": 0.0008469923000000022, "max": 0.1372656471, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0039784787222743034, "min": 0.0037159237544983625, "max": 0.35401442646980286, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0556987002491951, "min": 0.05202293395996094, "max": 2.4781010150909424, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 244.82644628099175, "min": 229.74436090225564, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29624.0, "min": 15984.0, "max": 33581.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7540999890615543, "min": -1.0000000521540642, "max": 1.7652796472785837, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 210.4919986873865, "min": -27.40020178258419, "max": 233.44319838285446, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7540999890615543, "min": -1.0000000521540642, "max": 1.7652796472785837, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 210.4919986873865, "min": -27.40020178258419, "max": 233.44319838285446, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.010277290528968782, "min": 0.009395239353040328, "max": 7.0145635502412915, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.2332748634762538, "min": 1.1556144404239603, "max": 112.23301680386066, "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": "1704180853", "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": "1704188251" }, "total": 7397.785799507, "count": 1, "self": 0.487953804999961, "children": { "run_training.setup": { "total": 0.05070797300004415, "count": 1, "self": 0.05070797300004415 }, "TrainerController.start_learning": { "total": 7397.247137729, "count": 1, "self": 4.487828219963376, "children": { "TrainerController._reset_env": { "total": 2.389873729000101, "count": 1, "self": 2.389873729000101 }, "TrainerController.advance": { "total": 7390.282588819037, "count": 194543, "self": 4.830883457932941, "children": { "env_step": { "total": 5442.492593306206, "count": 194543, "self": 5031.657655063065, "children": { "SubprocessEnvManager._take_step": { "total": 407.9656317351328, "count": 194543, "self": 15.107802824087003, "children": { "TorchPolicy.evaluate": { "total": 392.8578289110458, "count": 187558, "self": 392.8578289110458 } } }, "workers": { "total": 2.8693065080083215, "count": 194543, "self": 0.0, "children": { "worker_root": { "total": 7380.074546139183, "count": 194543, "is_parallel": true, "self": 2736.2670636172215, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016733469999508088, "count": 1, "is_parallel": true, "self": 0.0005037400003402581, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011696069996105507, "count": 8, "is_parallel": true, "self": 0.0011696069996105507 } } }, "UnityEnvironment.step": { "total": 0.09834997699999803, "count": 1, "is_parallel": true, "self": 0.0006288770000537625, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045333899993238447, "count": 1, "is_parallel": true, "self": 0.00045333899993238447 }, "communicator.exchange": { "total": 0.09561103000010007, "count": 1, "is_parallel": true, "self": 0.09561103000010007 }, "steps_from_proto": { "total": 0.0016567309999118152, "count": 1, "is_parallel": true, "self": 0.00033086000007642724, "children": { "_process_rank_one_or_two_observation": { "total": 0.001325870999835388, "count": 8, "is_parallel": true, "self": 0.001325870999835388 } } } } } } }, "UnityEnvironment.step": { "total": 4643.807482521962, "count": 194542, "is_parallel": true, "self": 109.76879566467142, "children": { "UnityEnvironment._generate_step_input": { "total": 78.8412126511248, "count": 194542, "is_parallel": true, "self": 78.8412126511248 }, "communicator.exchange": { "total": 4133.629546724945, "count": 194542, "is_parallel": true, "self": 4133.629546724945 }, "steps_from_proto": { "total": 321.5679274812212, "count": 194542, "is_parallel": true, "self": 66.70596753528139, "children": { "_process_rank_one_or_two_observation": { "total": 254.86195994593982, "count": 1556336, "is_parallel": true, "self": 254.86195994593982 } } } } } } } } } } }, "trainer_advance": { "total": 1942.9591120548985, "count": 194543, "self": 9.155705238845485, "children": { "process_trajectory": { "total": 413.69594578405054, "count": 194543, "self": 413.03856703905035, "children": { "RLTrainer._checkpoint": { "total": 0.6573787450001873, "count": 6, "self": 0.6573787450001873 } } }, "_update_policy": { "total": 1520.1074610320024, "count": 1405, "self": 906.977637279148, "children": { "TorchPPOOptimizer.update": { "total": 613.1298237528545, "count": 68355, "self": 613.1298237528545 } } } } } } }, "trainer_threads": { "total": 1.0909989214269444e-06, "count": 1, "self": 1.0909989214269444e-06 }, "TrainerController._save_models": { "total": 0.08684587000061583, "count": 1, "self": 0.0015934149996610358, "children": { "RLTrainer._checkpoint": { "total": 0.0852524550009548, "count": 1, "self": 0.0852524550009548 } } } } } } }