17 lines
1.1 KiB
Plaintext
17 lines
1.1 KiB
Plaintext
Avg reward: -0.208 | Avg tools/rollout: 0.9 | groups with variance: 4/4
|
|
Avg reward: 1.969 | Avg tools/rollout: 1.0 | groups with variance: 1/4
|
|
Avg reward: 0.854 | Avg tools/rollout: 1.0 | groups with variance: 4/4
|
|
Avg reward: 1.193 | Avg tools/rollout: 0.9 | groups with variance: 3/4
|
|
Avg reward: -2.094 | Avg tools/rollout: 0.8 | groups with variance: 3/4
|
|
Avg reward: 0.505 | Avg tools/rollout: 0.9 | groups with variance: 4/4
|
|
Avg reward: -0.141 | Avg tools/rollout: 0.8 | groups with variance: 4/4
|
|
Avg reward: -0.797 | Avg tools/rollout: 0.9 | groups with variance: 4/4
|
|
Avg reward: 0.307 | Avg tools/rollout: 0.9 | groups with variance: 3/4
|
|
Avg reward: -1.125 | Avg tools/rollout: 1.0 | groups with variance: 1/4
|
|
Avg reward: -1.359 | Avg tools/rollout: 0.9 | groups with variance: 4/4
|
|
Avg reward: 0.484 | Avg tools/rollout: 1.0 | groups with variance: 3/4
|
|
Avg reward: -0.073 | Avg tools/rollout: 0.9 | groups with variance: 4/4
|
|
Avg reward: 1.740 | Avg tools/rollout: 1.0 | groups with variance: 3/4
|
|
Avg reward: 0.635 | Avg tools/rollout: 1.0 | groups with variance: 3/4
|
|
Avg reward: 1.615 | Avg tools/rollout: 0.9 | groups with variance: 2/4
|