Note training-view · mainline · 200 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note raw-collection · mainline · 400 episodes. See dataset card for parent and model-round mapping.

Note training-view · mainline · 200 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 200 episodes. See dataset card for parent and model-round mapping.

Note training-view · mainline · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note raw-collection · mainline · 284 episodes. See dataset card for parent and model-round mapping.

Note training-view · mainline · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 200 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · mainline · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note raw-collection · mainline · 302 episodes. See dataset card for parent and model-round mapping.

Note training-view · mainline · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · mainline · 100 episodes. See dataset card for parent and model-round mapping.

Note training-view · ablation · 100 episodes. See dataset card for parent and model-round mapping.

Note raw-collection · mainline · 217 episodes. See dataset card for parent and model-round mapping.

Note training-view · mainline · 100 episodes. See dataset card for parent and model-round mapping.

Note policy-rollouts · supporting · 100 episodes. See dataset card for parent and model-round mapping.

Note R0–R3 evaluation outcomes and exact grids. 160 mainline seed results; named DIVL ablations are separate.

mulligan/sim-square-broad-r00-baseline-divl

Robotics • Updated 4 days ago

Note divl-agent · r00 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r00-baseline-first100-divl

Robotics • Updated 4 days ago

Note divl-agent · r00 · baseline-first100 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r00-baseline-first100-idql

Robotics • Updated 6 days ago

Note idql-agent · r00 · baseline-first100 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r00-baseline-idql

Robotics • Updated 6 days ago

Note idql-agent · r00 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r00-sobol-divl

Robotics • Updated 4 days ago

Note divl-agent · r00 · sobol · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r00-sobol-first100-divl

Robotics • Updated 4 days ago

Note divl-agent · r00 · sobol-first100 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r00-sobol-first100-idql

Robotics • Updated 6 days ago

Note idql-agent · r00 · sobol-first100 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r00-sobol-idql

Robotics • Updated 6 days ago

Note idql-agent · r00 · sobol · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-auto-filtered-bc-n1-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · auto-filtered-bc-n1 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-auto-iql-n32-divl

Robotics • Updated 4 days ago

Note divl-agent · r01 · auto-iql-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-auto-iql-n32-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · auto-iql-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-auto-iql-success-bc-n32-divl

Robotics • Updated 4 days ago

Note divl-agent · r01 · auto-iql-success-bc-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-auto-iql-success-bc-n32-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · auto-iql-success-bc-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-auto-plain-il-n1-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · auto-plain-il-n1 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-baseline-divl

Robotics • Updated 4 days ago

Note divl-agent · r01 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-baseline-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-baseline-straddled-auto-success-divl

Robotics • Updated 4 days ago

Note divl-agent · r01 · baseline-straddled-auto-success · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-baseline-straddled-auto-success-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · baseline-straddled-auto-success · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-mulligan-no-cf-divl

Robotics • Updated 4 days ago

Note divl-agent · r01 · mulligan-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-mulligan-no-cf-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · mulligan-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-mulligan-divl

Robotics • Updated 4 days ago • 1

Note divl-agent · r01 · mulligan · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-mulligan-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · mulligan · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-sobol-with-cf-divl

Robotics • Updated 4 days ago

Note divl-agent · r01 · sobol-with-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-sobol-with-cf-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · sobol-with-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-sobol-no-cf-divl

Robotics • Updated 4 days ago

Note divl-agent · r01 · sobol-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r01-sobol-no-cf-idql

Robotics • Updated 6 days ago

Note idql-agent · r01 · sobol-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-auto-filtered-bc-n1-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · auto-filtered-bc-n1 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-auto-iql-n32-divl

Robotics • Updated 4 days ago

Note divl-agent · r02 · auto-iql-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-auto-iql-n32-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · auto-iql-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-auto-iql-success-bc-n32-divl

Robotics • Updated 4 days ago

Note divl-agent · r02 · auto-iql-success-bc-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-auto-iql-success-bc-n32-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · auto-iql-success-bc-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-auto-plain-il-n1-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · auto-plain-il-n1 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-baseline-divl

Robotics • Updated 4 days ago

Note divl-agent · r02 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-baseline-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-mulligan-no-cf-divl

Robotics • Updated 4 days ago

Note divl-agent · r02 · mulligan-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-mulligan-no-cf-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · mulligan-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-mulligan-divl

Robotics • Updated 4 days ago

Note divl-agent · r02 · mulligan · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-mulligan-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · mulligan · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-sobol-with-cf-divl

Robotics • Updated 4 days ago

Note divl-agent · r02 · sobol-with-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-sobol-with-cf-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · sobol-with-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-sobol-no-cf-divl

Robotics • Updated 4 days ago

Note divl-agent · r02 · sobol-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r02-sobol-no-cf-idql

Robotics • Updated 6 days ago

Note idql-agent · r02 · sobol-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-auto-filtered-bc-n1-idql

Robotics • Updated 6 days ago

Note idql-agent · r03 · auto-filtered-bc-n1 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-auto-iql-n32-divl

Robotics • Updated 4 days ago

Note divl-agent · r03 · auto-iql-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-auto-iql-n32-idql

Robotics • Updated 6 days ago

Note idql-agent · r03 · auto-iql-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-auto-iql-success-bc-n32-divl

Robotics • Updated 4 days ago

Note divl-agent · r03 · auto-iql-success-bc-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-auto-iql-success-bc-n32-idql

Robotics • Updated 6 days ago

Note idql-agent · r03 · auto-iql-success-bc-n32 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-auto-plain-il-n1-idql

Robotics • Updated 6 days ago

Note idql-agent · r03 · auto-plain-il-n1 · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-baseline-divl

Robotics • Updated 4 days ago

Note divl-agent · r03 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-baseline-idql

Robotics • Updated 6 days ago

Note idql-agent · r03 · baseline · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-mulligan-no-cf-divl

Robotics • Updated 4 days ago

Note divl-agent · r03 · mulligan-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-mulligan-no-cf-idql

Robotics • Updated 6 days ago

Note idql-agent · r03 · mulligan-no-cf · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-mulligan-divl

Robotics • Updated 4 days ago

Note divl-agent · r03 · mulligan · 5 checkpoint(s). See model card for training data and evaluations.

mulligan/sim-square-broad-r03-mulligan-idql

Robotics • Updated 6 days ago

Note idql-agent · r03 · mulligan · 5 checkpoint(s). See model card for training data and evaluations.