ppo-SnowballTarget / results.json
Vladprime's picture
Add trained Unity PPO policy, ONNX export and independent evaluation
449ddfe verified
Raw History Blame Contribute Delete
6.27 kB
{
"mean_reward": 6.636363636363637,
"std_reward": 2.0790175683689585,
"mean_minus_std": 4.557346067994678,
"n_eval_agent_episodes": 44,
"episode_rewards": [
6.0,
7.0,
10.0,
10.0,
5.0,
4.0,
4.0,
4.0,
8.0,
4.0,
7.0,
7.0,
9.0,
5.0,
9.0,
6.0,
7.0,
6.0,
6.0,
6.0,
7.0,
5.0,
5.0,
4.0,
9.0,
0.0,
7.0,
6.0,
6.0,
11.0,
10.0,
5.0,
7.0,
9.0,
7.0,
9.0,
7.0,
5.0,
6.0,
9.0,
7.0,
7.0,
6.0,
8.0
],
"records": [
{
"behavior": "SnowballTarget?team=0",
"agent_id": 0,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 1,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 2,
"reward": 10.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 3,
"reward": 10.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 4,
"reward": 5.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 5,
"reward": 4.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 6,
"reward": 4.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 7,
"reward": 4.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 8,
"reward": 8.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 9,
"reward": 4.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 10,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 0,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 1,
"reward": 9.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 2,
"reward": 5.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 3,
"reward": 9.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 4,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 5,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 6,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 7,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 8,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 9,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 10,
"reward": 5.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 0,
"reward": 5.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 1,
"reward": 4.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 2,
"reward": 9.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 3,
"reward": 0.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 4,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 5,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 6,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 7,
"reward": 11.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 8,
"reward": 10.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 9,
"reward": 5.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 10,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 0,
"reward": 9.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 1,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 2,
"reward": 9.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 3,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 4,
"reward": 5.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 5,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 6,
"reward": 9.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 7,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 8,
"reward": 7.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 9,
"reward": 6.0,
"interrupted": true
},
{
"behavior": "SnowballTarget?team=0",
"agent_id": 10,
"reward": 8.0,
"interrupted": true
}
],
"evaluation_seed": 1000000,
"eval_datetime": "2026-11-01T13:06:49.043568+00:00",
"evaluation_kind": "separate Unity process, ONNX policy, completed agent episodes (soccer episodes within a match are correlated)"
}