{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23889672756195068, "min": 0.23889672756195068, "max": 1.4533013105392456, "count": 42 }, "Pyramids.Policy.Entropy.sum": { "value": 7243.3486328125, "min": 7243.3486328125, "max": 44087.34765625, "count": 42 }, "Pyramids.Step.mean": { "value": 1259947.0, "min": 29952.0, "max": 1259947.0, "count": 42 }, "Pyramids.Step.sum": { "value": 1259947.0, "min": 29952.0, "max": 1259947.0, "count": 42 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7594929933547974, "min": -0.08174017071723938, "max": 0.7594929933547974, "count": 42 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 221.77195739746094, "min": -19.7811222076416, "max": 221.77195739746094, "count": 42 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006989995017647743, "min": -0.033844709396362305, "max": 0.21716365218162537, "count": 42 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.041078567504883, "min": -9.27345085144043, "max": 52.11927795410156, "count": 42 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07044205685365124, "min": 0.06443278590792462, "max": 0.07379906093206874, "count": 42 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9861887959511173, "min": 0.4945134187715018, "max": 1.0713612716034393, "count": 42 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016031872148492506, "min": 0.0012379062057475275, "max": 0.017437861616989334, "count": 42 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2244462100788951, "min": 0.009515148951124148, "max": 0.24413006263785067, "count": 42 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00017543372009353568, "min": 0.00017543372009353568, "max": 0.00029838354339596195, "count": 42 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0024560720813094996, "min": 0.0020691136102954665, "max": 0.004011093462968867, "count": 42 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1584778928571429, "min": 0.1584778928571429, "max": 0.19946118095238097, "count": 42 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2186905000000006, "min": 1.3897045333333333, "max": 2.7675261333333334, "count": 42 }, "Pyramids.Policy.Beta.mean": { "value": 0.005851941496428571, "min": 0.005851941496428571, "max": 0.009946171977142856, "count": 42 }, "Pyramids.Policy.Beta.sum": { "value": 0.08192718095, "min": 0.06897148288, "max": 0.13370941022, "count": 42 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008044026792049408, "min": 0.007929275743663311, "max": 0.4216306507587433, "count": 42 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11261637508869171, "min": 0.1110098659992218, "max": 2.9514145851135254, "count": 42 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 256.7967479674797, "min": 256.7967479674797, "max": 999.0, "count": 42 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31586.0, "min": 15984.0, "max": 32801.0, "count": 42 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.743637081956671, "min": -1.0000000521540642, "max": 1.743637081956671, "count": 42 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 216.21099816262722, "min": -32.000001668930054, "max": 216.21099816262722, "count": 42 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.743637081956671, "min": -1.0000000521540642, "max": 1.743637081956671, "count": 42 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 216.21099816262722, "min": -32.000001668930054, "max": 216.21099816262722, "count": 42 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02141749126800982, "min": 0.02141749126800982, "max": 9.007291312329471, "count": 42 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6557689172332175, "min": 2.433480086911004, "max": 144.11666099727154, "count": 42 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 42 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 42 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1775406665", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1775411015" }, "total": 4350.630000815, "count": 1, "self": 0.8015553210007056, "children": { "run_training.setup": { "total": 0.03152046000013797, "count": 1, "self": 0.03152046000013797 }, "TrainerController.start_learning": { "total": 4349.796925033999, "count": 1, "self": 2.8077655287561356, "children": { "TrainerController._reset_env": { "total": 2.5021293449999575, "count": 1, "self": 2.5021293449999575 }, "TrainerController.advance": { "total": 4344.486011046242, "count": 82119, "self": 3.209275068545139, "children": { "env_step": { "total": 2946.2607182449965, "count": 82119, "self": 2739.394981543952, "children": { "SubprocessEnvManager._take_step": { "total": 205.00980215110667, "count": 82119, "self": 9.059574826047537, "children": { "TorchPolicy.evaluate": { "total": 195.95022732505913, "count": 80181, "self": 195.95022732505913 } } }, "workers": { "total": 1.855934549937956, "count": 82118, "self": 0.0, "children": { "worker_root": { "total": 4338.704728138195, "count": 82118, "is_parallel": true, "self": 1836.0873166691763, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021319620000213035, "count": 1, "is_parallel": true, "self": 0.0007075770008668769, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014243849991544266, "count": 8, "is_parallel": true, "self": 0.0014243849991544266 } } }, "UnityEnvironment.step": { "total": 0.1399350619994948, "count": 1, "is_parallel": true, "self": 0.0006462129986175569, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004752830000143149, "count": 1, "is_parallel": true, "self": 0.0004752830000143149 }, "communicator.exchange": { "total": 0.1345375500004593, "count": 1, "is_parallel": true, "self": 0.1345375500004593 }, "steps_from_proto": { "total": 0.004276016000403615, "count": 1, "is_parallel": true, "self": 0.00042334600311733084, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038526699972862843, "count": 8, "is_parallel": true, "self": 0.0038526699972862843 } } } } } } }, "UnityEnvironment.step": { "total": 2502.6174114690184, "count": 82117, "is_parallel": true, "self": 59.840787372430896, "children": { "UnityEnvironment._generate_step_input": { "total": 40.29256038983749, "count": 82117, "is_parallel": true, "self": 40.29256038983749 }, "communicator.exchange": { "total": 2213.1807789817485, "count": 82117, "is_parallel": true, "self": 2213.1807789817485 }, "steps_from_proto": { "total": 189.3032847250015, "count": 82117, "is_parallel": true, "self": 37.46266512181319, "children": { "_process_rank_one_or_two_observation": { "total": 151.84061960318832, "count": 656936, "is_parallel": true, "self": 151.84061960318832 } } } } } } } } } } }, "trainer_advance": { "total": 1395.0160177327007, "count": 82118, "self": 5.61621242954061, "children": { "process_trajectory": { "total": 206.03014717217684, "count": 82118, "self": 205.8578435081772, "children": { "RLTrainer._checkpoint": { "total": 0.17230366399962804, "count": 2, "self": 0.17230366399962804 } } }, "_update_policy": { "total": 1183.3696581309832, "count": 583, "self": 466.862065635054, "children": { "TorchPPOOptimizer.update": { "total": 716.5075924959292, "count": 29193, "self": 716.5075924959292 } } } } } } }, "trainer_threads": { "total": 1.6230005712714046e-06, "count": 1, "self": 1.6230005712714046e-06 }, "TrainerController._save_models": { "total": 0.0010174910003115656, "count": 1, "self": 3.384299998288043e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0009836480003286852, "count": 1, "self": 0.0009836480003286852 } } } } } } }