ppo-PyramidsRND / results.json
Vladprime's picture
Add trained PPO RND policy, original configuration and separate ONNX evaluation
795b5aa verified
Raw History Blame Contribute Delete
8.06 kB
{
"mean_reward": -0.8986040989945346,
"std_reward": 0.48686846265775247,
"mean_minus_std": -1.3854725616522872,
"n_eval_agent_episodes": 48,
"episode_rewards": [
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
1.3160000471398234,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
1.5510000309441239,
-0.9999999311257852,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295
],
"records": [
{
"behavior": "Pyramids?team=0",
"agent_id": 0,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 1,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 2,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 3,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 4,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 5,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 6,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 7,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 8,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 9,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 10,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 11,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 12,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 13,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 14,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 15,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 10,
"reward": 1.3160000471398234,
"interrupted": false
},
{
"behavior": "Pyramids?team=0",
"agent_id": 0,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 1,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 2,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 3,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 4,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 5,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 6,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 7,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 8,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 9,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 11,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 12,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 13,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 14,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 15,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 12,
"reward": 1.5510000309441239,
"interrupted": false
},
{
"behavior": "Pyramids?team=0",
"agent_id": 10,
"reward": -0.9999999311257852,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 0,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 1,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 2,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 3,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 4,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 5,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 6,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 7,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 8,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 9,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 11,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 13,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 14,
"reward": -0.9999999310821295,
"interrupted": true
},
{
"behavior": "Pyramids?team=0",
"agent_id": 15,
"reward": -0.9999999310821295,
"interrupted": true
}
],
"evaluation_seed": 1000000,
"eval_datetime": "2026-11-01T13:09:03.627062+00:00",
"evaluation_kind": "separate Unity process, ONNX policy, completed agent episodes (soccer episodes within a match are correlated)"
}