{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8525972962379456, "min": 0.7685958743095398, "max": 1.4148558378219604, "count": 6 }, "Pyramids.Policy.Entropy.sum": { "value": 25687.05078125, "min": 23107.06640625, "max": 42921.06640625, "count": 6 }, "Pyramids.Step.mean": { "value": 179976.0, "min": 29999.0, "max": 179976.0, "count": 6 }, "Pyramids.Step.sum": { "value": 179976.0, "min": 29999.0, "max": 179976.0, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06478046625852585, "min": -0.17248746752738953, "max": -0.06478046625852585, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.676873207092285, "min": -41.05201721191406, "max": -15.676873207092285, "count": 6 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.08444657921791077, "min": 0.08444657921791077, "max": 0.3411673903465271, "count": 6 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 20.436071395874023, "min": 20.436071395874023, "max": 81.88017272949219, "count": 6 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06848841694629206, "min": 0.06645446432290963, "max": 0.07442661318584726, "count": 6 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9588378372480887, "min": 0.595412905486778, "max": 0.9588378372480887, "count": 6 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0022097700208396237, "min": 0.00028507633900457706, "max": 0.010728728211535882, "count": 6 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03093678029175473, "min": 0.0031358397290503475, "max": 0.08582982569228706, "count": 6 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002835495769120475, "min": 0.0002835495769120475, "max": 0.00029840696303101244, "count": 6 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003969694076768665, "min": 0.0023872557042480995, "max": 0.003969694076768665, "count": 6 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19451652380952383, "min": 0.19451652380952383, "max": 0.19946898750000003, "count": 6 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.7232313333333336, "min": 1.5957519000000002, "max": 2.7232313333333336, "count": 6 }, "Pyramids.Policy.Beta.mean": { "value": 0.009452200728571428, "min": 0.009452200728571428, "max": 0.00994695185125, "count": 6 }, "Pyramids.Policy.Beta.sum": { "value": 0.13233081019999998, "min": 0.07957561481, "max": 0.13233081019999998, "count": 6 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.06705036759376526, "min": 0.06705036759376526, "max": 0.6905897259712219, "count": 6 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.9387051463127136, "min": 0.9387051463127136, "max": 5.524717807769775, "count": 6 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 943.4516129032259, "min": 943.4516129032259, "max": 999.0, "count": 6 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29247.0, "min": 15903.0, "max": 32265.0, "count": 6 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.6216258548440472, "min": -0.999987552408129, "max": -0.5888727819829276, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -19.270401500165462, "min": -31.999601677060127, "max": -13.918000780045986, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.6216258548440472, "min": -0.999987552408129, "max": -0.5888727819829276, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -19.270401500165462, "min": -31.999601677060127, "max": -13.918000780045986, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 0.6561870046500717, "min": 0.6561870046500717, "max": 13.471240378916264, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 20.341797144152224, "min": 20.341797144152224, "max": 215.53984606266022, "count": 6 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1734345721", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734346158" }, "total": 437.57680742, "count": 1, "self": 0.4788514070000929, "children": { "run_training.setup": { "total": 0.055545781000091665, "count": 1, "self": 0.055545781000091665 }, "TrainerController.start_learning": { "total": 437.04241023199984, "count": 1, "self": 0.3046039039959396, "children": { "TrainerController._reset_env": { "total": 2.066780240999833, "count": 1, "self": 2.066780240999833 }, "TrainerController.advance": { "total": 434.34583015300404, "count": 12589, "self": 0.31472872200356505, "children": { "env_step": { "total": 294.3329148910093, "count": 12589, "self": 260.373176297001, "children": { "SubprocessEnvManager._take_step": { "total": 33.77240578397914, "count": 12589, "self": 0.9903168230011943, "children": { "TorchPolicy.evaluate": { "total": 32.782088960977944, "count": 12546, "self": 32.782088960977944 } } }, "workers": { "total": 0.18733281002914737, "count": 12588, "self": 0.0, "children": { "worker_root": { "total": 435.69762289705704, "count": 12588, "is_parallel": true, "self": 199.80945987904624, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024325839999619348, "count": 1, "is_parallel": true, "self": 0.0009537169989926042, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014788670009693305, "count": 8, "is_parallel": true, "self": 0.0014788670009693305 } } }, "UnityEnvironment.step": { "total": 0.050896321999971406, "count": 1, "is_parallel": true, "self": 0.0005599350001830317, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005067689999123104, "count": 1, "is_parallel": true, "self": 0.0005067689999123104 }, "communicator.exchange": { "total": 0.04808272299987948, "count": 1, "is_parallel": true, "self": 0.04808272299987948 }, "steps_from_proto": { "total": 0.0017468949999965844, "count": 1, "is_parallel": true, "self": 0.0004280309999558085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013188640000407759, "count": 8, "is_parallel": true, "self": 0.0013188640000407759 } } } } } } }, "UnityEnvironment.step": { "total": 235.8881630180108, "count": 12587, "is_parallel": true, "self": 6.59218486409236, "children": { "UnityEnvironment._generate_step_input": { "total": 4.654961781996462, "count": 12587, "is_parallel": true, "self": 4.654961781996462 }, "communicator.exchange": { "total": 204.33458181894184, "count": 12587, "is_parallel": true, "self": 204.33458181894184 }, "steps_from_proto": { "total": 20.306434552980136, "count": 12587, "is_parallel": true, "self": 4.244187505000809, "children": { "_process_rank_one_or_two_observation": { "total": 16.062247047979326, "count": 100696, "is_parallel": true, "self": 16.062247047979326 } } } } } } } } } } }, "trainer_advance": { "total": 139.69818653999118, "count": 12588, "self": 0.4824562690005223, "children": { "process_trajectory": { "total": 24.855625302993303, "count": 12588, "self": 24.855625302993303 }, "_update_policy": { "total": 114.36010496799736, "count": 76, "self": 63.804899489011405, "children": { "TorchPPOOptimizer.update": { "total": 50.555205478985954, "count": 4593, "self": 50.555205478985954 } } } } } } }, "trainer_threads": { "total": 1.690000317466911e-06, "count": 1, "self": 1.690000317466911e-06 }, "TrainerController._save_models": { "total": 0.32519424399970376, "count": 1, "self": 0.003326080000078946, "children": { "RLTrainer._checkpoint": { "total": 0.3218681639996248, "count": 1, "self": 0.3218681639996248 } } } } } } }