{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3721298277378082, "min": 0.3721298277378082, "max": 1.4631677865982056, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11217.4814453125, "min": 11217.4814453125, "max": 44386.65625, "count": 33 }, "Pyramids.Step.mean": { "value": 989933.0, "min": 29927.0, "max": 989933.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989933.0, "min": 29927.0, "max": 989933.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.507165253162384, "min": -0.07950711995363235, "max": 0.5134052038192749, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.45611572265625, "min": -19.161216735839844, "max": 140.1596221923828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.042967602610588074, "min": -0.07552078366279602, "max": 0.5458242893218994, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.730155944824219, "min": -19.48436164855957, "max": 129.3603515625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06944972194349054, "min": 0.06499858879525323, "max": 0.07172881632970571, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9722961072088676, "min": 0.5736713292705896, "max": 1.061178544710856, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01413840736375084, "min": 0.0010005697230526093, "max": 0.01641102178178872, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19793770309251177, "min": 0.01300740639968392, "max": 0.22975430494504204, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.523497492200005e-06, "min": 7.523497492200005e-06, "max": 0.00029484281421906253, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010532896489080006, "min": 0.00010532896489080006, "max": 0.0036341248886250996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250780000000002, "min": 0.10250780000000002, "max": 0.1982809375, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351092000000003, "min": 1.4351092000000003, "max": 2.6113749000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026052922000000016, "min": 0.00026052922000000016, "max": 0.00982826565625, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003647409080000002, "min": 0.003647409080000002, "max": 0.12115635251, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01195572130382061, "min": 0.011577912606298923, "max": 0.5830198526382446, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16738009452819824, "min": 0.16209077835083008, "max": 4.664158821105957, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.39506172839504, "min": 358.1111111111111, "max": 985.5151515151515, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30974.0, "min": 16470.0, "max": 34143.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5435061567911394, "min": -0.865193993304715, "max": 1.6122052402872789, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.0239987000823, "min": -28.551401779055595, "max": 131.49499844014645, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5435061567911394, "min": -0.865193993304715, "max": 1.6122052402872789, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.0239987000823, "min": -28.551401779055595, "max": 131.49499844014645, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04716946320506934, "min": 0.043745191587731824, "max": 11.577297255396843, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8207265196106164, "min": 3.4837097307899967, "max": 196.81405334174633, "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": "1778568047", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/home/oleksii/PycharmProjects/flock_systems/snowball/.venv/bin/mlagents-learn ../ml-agents/config/ppo/PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1778569384" }, "total": 1337.0605949490127, "count": 1, "self": 0.2704082430136623, "children": { "run_training.setup": { "total": 0.0167295769933844, "count": 1, "self": 0.0167295769933844 }, "TrainerController.start_learning": { "total": 1336.7734571290057, "count": 1, "self": 1.3198955350817414, "children": { "TrainerController._reset_env": { "total": 2.2738781350053614, "count": 1, "self": 2.2738781350053614 }, "TrainerController.advance": { "total": 1333.1114175309194, "count": 63851, "self": 1.2053866192582063, "children": { "env_step": { "total": 811.6138867348491, "count": 63851, "self": 680.7334460404381, "children": { "SubprocessEnvManager._take_step": { "total": 130.1087740995281, "count": 63851, "self": 3.718510408332804, "children": { "TorchPolicy.evaluate": { "total": 126.39026369119529, "count": 62566, "self": 126.39026369119529 } } }, "workers": { "total": 0.771666594882845, "count": 63851, "self": 0.0, "children": { "worker_root": { "total": 1335.116527579914, "count": 63851, "is_parallel": true, "self": 734.1928287652117, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004252982995240018, "count": 1, "is_parallel": true, "self": 0.003337507994729094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009154750005109236, "count": 8, "is_parallel": true, "self": 0.0009154750005109236 } } }, "UnityEnvironment.step": { "total": 0.03323493100469932, "count": 1, "is_parallel": true, "self": 0.00021658701007254422, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020277001021895558, "count": 1, "is_parallel": true, "self": 0.00020277001021895558 }, "communicator.exchange": { "total": 0.032114932997501455, "count": 1, "is_parallel": true, "self": 0.032114932997501455 }, "steps_from_proto": { "total": 0.0007006409869063646, "count": 1, "is_parallel": true, "self": 0.00016536099428776652, "children": { "_process_rank_one_or_two_observation": { "total": 0.000535279992618598, "count": 8, "is_parallel": true, "self": 0.000535279992618598 } } } } } } }, "UnityEnvironment.step": { "total": 600.9236988147022, "count": 63850, "is_parallel": true, "self": 16.4270242825296, "children": { "UnityEnvironment._generate_step_input": { "total": 12.486227350949775, "count": 63850, "is_parallel": true, "self": 12.486227350949775 }, "communicator.exchange": { "total": 522.3921993876575, "count": 63850, "is_parallel": true, "self": 522.3921993876575 }, "steps_from_proto": { "total": 49.61824779356539, "count": 63850, "is_parallel": true, "self": 11.634505377733149, "children": { "_process_rank_one_or_two_observation": { "total": 37.98374241583224, "count": 510800, "is_parallel": true, "self": 37.98374241583224 } } } } } } } } } } }, "trainer_advance": { "total": 520.2921441768121, "count": 63851, "self": 2.3081628090149025, "children": { "process_trajectory": { "total": 91.56261578387057, "count": 63851, "self": 91.39523165486753, "children": { "RLTrainer._checkpoint": { "total": 0.16738412900303956, "count": 2, "self": 0.16738412900303956 } } }, "_update_policy": { "total": 426.4213655839267, "count": 458, "self": 225.89709006053454, "children": { "TorchPPOOptimizer.update": { "total": 200.52427552339213, "count": 22773, "self": 200.52427552339213 } } } } } } }, "trainer_threads": { "total": 6.24000676907599e-07, "count": 1, "self": 6.24000676907599e-07 }, "TrainerController._save_models": { "total": 0.06826530399848707, "count": 1, "self": 0.0009729219891596586, "children": { "RLTrainer._checkpoint": { "total": 0.06729238200932741, "count": 1, "self": 0.06729238200932741 } } } } } } }