Forkits
/

MLAgents-Walker

Reinforcement Learning

unity-ml-agents

deep-reinforcement-learning

ML-Agents-Walker

Model card Files Files and versions Metrics Training metrics Community

MLAgents-Walker / run_logs /training_status.json

Forkits's picture

Trained Walker agent upload

d8e1095 almost 2 years ago

raw history blame contribute delete

No virus

2.46 kB

	{
	"Walker": {
	"checkpoints": [
	{
	"steps": 5499802,
	"file_path": "results\\Walker Training\\Walker\\Walker-5499802.onnx",
	"reward": 922.7136942545573,
	"creation_time": 1656319104.8587525,
	"auxillary_file_paths": [
	"results\\Walker Training\\Walker\\Walker-5499802.pt"
	]
	},
	{
	"steps": 5999264,
	"file_path": "results\\Walker Training\\Walker\\Walker-5999264.onnx",
	"reward": 725.7388473272324,
	"creation_time": 1656321554.0934162,
	"auxillary_file_paths": [
	"results\\Walker Training\\Walker\\Walker-5999264.pt"
	]
	},
	{
	"steps": 6499395,
	"file_path": "results\\Walker Training\\Walker\\Walker-6499395.onnx",
	"reward": 832.2816411554813,
	"creation_time": 1656324010.2904415,
	"auxillary_file_paths": [
	"results\\Walker Training\\Walker\\Walker-6499395.pt"
	]
	},
	{
	"steps": 6999731,
	"file_path": "results\\Walker Training\\Walker\\Walker-6999731.onnx",
	"reward": 903.6871415918523,
	"creation_time": 1656326314.9925528,
	"auxillary_file_paths": [
	"results\\Walker Training\\Walker\\Walker-6999731.pt"
	]
	},
	{
	"steps": 7023015,
	"file_path": "results\\Walker Training\\Walker\\Walker-7023015.onnx",
	"reward": 1021.1286127120256,
	"creation_time": 1656326420.1491082,
	"auxillary_file_paths": [
	"results\\Walker Training\\Walker\\Walker-7023015.pt"
	]
	}
	],
	"final_checkpoint": {
	"steps": 7023015,
	"file_path": "results\\Walker Training\\Walker.onnx",
	"reward": 1021.1286127120256,
	"creation_time": 1656326420.1491082,
	"auxillary_file_paths": [
	"results\\Walker Training\\Walker\\Walker-7023015.pt"
	]
	}
	},
	"metadata": {
	"stats_format_version": "0.3.0",
	"mlagents_version": "0.29.0.dev0",
	"torch_version": "1.11.0"
	}
	}