Dataset Cards - CFCQL

Dataset Cards - CFCQL

6h_vs_8z

6h_vs_8z - Download

Metadata

Environment nameVersionAgentsAction typeObservation sizeReward type
SMAC (v1)SMAC V1, from OxWhiRL6Discrete[78]Dense

Generation procedure for each dataset

Converted from cfcql format to a Vault.

Summary statistics

UidEpisode return meanMin returnMax returnTransitionsTrajectoriesJoint SACo
Mixed17.81 ± 2.889.1420.1721772350000.24
Medium-Replay12.97 ± 2.220.8120.0318240350001.00
Medium16.63 ± 3.039.8020.0020700850000.12
Expert19.01 ± 2.119.1420.1722812050000.12

3s_vs_5z

3s_vs_5z - Download

Metadata

Environment nameVersionAgentsAction typeObservation sizeReward type
SMAC (v1)SMAC V1, from OxWhiRL3Discrete[48]Dense

Generation procedure for each dataset

Converted from cfcql format to a Vault.

Summary statistics

UidEpisode return meanMin returnMax returnTransitionsTrajectoriesJoint SACo
Mixed21.04 ± 2.515.5829.0088837550000.23
Medium-Replay18.85 ± 4.204.0328.53108273950000.99
Medium20.86 ± 3.475.5829.00117457650000.11
Expert21.19 ± 0.709.2124.8760052050000.12

5m_vs_6m

5m_vs_6m - Download

Metadata

Environment nameVersionAgentsAction typeObservation sizeReward type
SMAC (v1)SMAC V1, from OxWhiRL5Discrete[55]Dense

Generation procedure for each dataset

Converted from cfcql format to a Vault.

Summary statistics

UidEpisode return meanMin returnMax returnTransitionsTrajectoriesJoint SACo
Mixed15.11 ± 5.116.3820.0013170350000.22
Medium-Replay9.02 ± 2.594.5720.0011840550000.96
Medium12.05 ± 4.366.3820.0013525650000.10
Expert18.17 ± 3.797.1320.0012853650000.12

2s3z

2s3z - Download

Metadata

Environment nameVersionAgentsAction typeObservation sizeReward type
SMAC (v1)SMAC V1, from OxWhiRL5Discrete[80]Dense

Generation procedure for each dataset

Converted from cfcql format to a Vault.

Summary statistics

UidEpisode return meanMin returnMax returnTransitionsTrajectoriesJoint SACo
Mixed16.39 ± 4.337.9620.2723252850000.25
Medium-Replay7.94 ± 3.412.0020.1210012119761.00
Medium12.76 ± 3.327.9620.2725399250000.12
Expert19.97 ± 0.3713.9020.0821183250000.12