{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.4068665504455566, "min": 2.4068665504455566, "max": 2.875962257385254, "count": 5 }, "SnowballTarget.Policy.Entropy.sum": { "value": 24489.8671875, "min": 24489.8671875, "max": 29642.54296875, "count": 5 }, "SnowballTarget.Step.mean": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Step.sum": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.115147113800049, "min": 0.40806296467781067, "max": 4.115147113800049, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 798.3385009765625, "min": 79.16421508789062, "max": 798.3385009765625, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07005781891510142, "min": 0.059381619710870394, "max": 0.07005781891510142, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2802312756604057, "min": 0.23752647884348158, "max": 0.32589076537588685, "count": 5 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24973559459927036, "min": 0.12096577631788986, "max": 0.2633334485339183, "count": 5 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9989423783970814, "min": 0.48386310527155946, "max": 1.3166672426695916, "count": 5 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.9928090024000003e-05, "min": 2.9928090024000003e-05, "max": 0.00026752801082399996, "count": 5 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00011971236009600001, "min": 0.00011971236009600001, "max": 0.0010701120432959998, "count": 5 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10997600000000002, "min": 0.10997600000000002, "max": 0.18917599999999998, "count": 5 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4399040000000001, "min": 0.4399040000000001, "max": 0.8468800000000001, "count": 5 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0005078024, "min": 0.0005078024, "max": 0.0044598824, "count": 5 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0020312096, "min": 0.0020312096, "max": 0.0178395296, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 10.454545454545455, "min": 3.590909090909091, "max": 10.454545454545455, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 460.0, "min": 158.0, "max": 492.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 10.454545454545455, "min": 3.590909090909091, "max": 10.454545454545455, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 460.0, "min": 158.0, "max": 492.0, "count": 5 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721349030", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721349155" }, "total": 125.03761097100005, "count": 1, "self": 0.4328856900001483, "children": { "run_training.setup": { "total": 0.07854101299994909, "count": 1, "self": 0.07854101299994909 }, "TrainerController.start_learning": { "total": 124.52618426799995, "count": 1, "self": 0.2107322000002796, "children": { "TrainerController._reset_env": { "total": 2.8790511250000463, "count": 1, "self": 2.8790511250000463 }, "TrainerController.advance": { "total": 121.32789357099955, "count": 4612, "self": 0.07269133900013003, "children": { "env_step": { "total": 121.25520223199942, "count": 4612, "self": 80.00339783399943, "children": { "SubprocessEnvManager._take_step": { "total": 41.17986371700124, "count": 4612, "self": 0.3768554020044803, "children": { "TorchPolicy.evaluate": { "total": 40.80300831499676, "count": 4612, "self": 40.80300831499676 } } }, "workers": { "total": 0.0719406809987504, "count": 4612, "self": 0.0, "children": { "worker_root": { "total": 124.11262741299686, "count": 4612, "is_parallel": true, "self": 64.39389351000148, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008103145999939443, "count": 1, "is_parallel": true, "self": 0.005966528999806542, "children": { "_process_rank_one_or_two_observation": { "total": 0.002136617000132901, "count": 10, "is_parallel": true, "self": 0.002136617000132901 } } }, "UnityEnvironment.step": { "total": 0.037300041999969835, "count": 1, "is_parallel": true, "self": 0.0006181939999123642, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039423100008662004, "count": 1, "is_parallel": true, "self": 0.00039423100008662004 }, "communicator.exchange": { "total": 0.03443223599992962, "count": 1, "is_parallel": true, "self": 0.03443223599992962 }, "steps_from_proto": { "total": 0.001855381000041234, "count": 1, "is_parallel": true, "self": 0.00037131000010504067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014840709999361934, "count": 10, "is_parallel": true, "self": 0.0014840709999361934 } } } } } } }, "UnityEnvironment.step": { "total": 59.71873390299538, "count": 4611, "is_parallel": true, "self": 2.5856044029912937, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3710803910099685, "count": 4611, "is_parallel": true, "self": 1.3710803910099685 }, "communicator.exchange": { "total": 46.994615585998986, "count": 4611, "is_parallel": true, "self": 46.994615585998986 }, "steps_from_proto": { "total": 8.767433522995134, "count": 4611, "is_parallel": true, "self": 1.6769655100181353, "children": { "_process_rank_one_or_two_observation": { "total": 7.090468012976999, "count": 46110, "is_parallel": true, "self": 7.090468012976999 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004267460001301515, "count": 1, "self": 0.0004267460001301515, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 119.86053349498218, "count": 178609, "is_parallel": true, "self": 3.868341434943545, "children": { "process_trajectory": { "total": 66.71842147003838, "count": 178609, "is_parallel": true, "self": 66.14001820203828, "children": { "RLTrainer._checkpoint": { "total": 0.5784032680001019, "count": 1, "is_parallel": true, "self": 0.5784032680001019 } } }, "_update_policy": { "total": 49.273770590000254, "count": 22, "is_parallel": true, "self": 16.691510459997744, "children": { "TorchPPOOptimizer.update": { "total": 32.58226013000251, "count": 1119, "is_parallel": true, "self": 32.58226013000251 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10808062599994628, "count": 1, "self": 0.0009791790000690526, "children": { "RLTrainer._checkpoint": { "total": 0.10710144699987723, "count": 1, "self": 0.10710144699987723 } } } } } } }