List your company
ResearchFormerly WizWand

Reinforcement Learning on Block Sliding

106Retention (Task 1)Multi-task
-9.4420.5350.580.47Sep 25, 2020
Updated 5mo ago

Evaluation results

MethodLinks
Multi-task2020.09106131103113113
Multi-taskTarget Network=MLP (2x200), Hypernetwork=MLP (2x50)2020.09106131103113113
HyperCRL2020.0982981099596
HyperCRLTarget Network=MLP (2x200), Hypernetwork=MLP (2x50)2020.0982981099596
Coreset2020.095897657373
CoresetTarget Network=MLP (2x200), Hypernetwork=MLP (2x50)2020.095897657373
SI2020.0937926810375
SITarget Network=MLP (2x200), Hypernetwork=MLP (2x50)2020.0937926810375
Finetuning2020.09-2-12-1-7-6
FinetuningTarget Network=MLP (2x200), Hypernetwork=MLP (2x50)2020.09-2-12-1-7-6
EWC2020.09-514133915
EWCTarget Network=MLP (2x200), Hypernetwork=MLP (2x50)2020.09-514133915