Sparse Rewards as Preferences: Investigating Reward Shaping with Preference-Based RL Methods in Sparse Reward Domains.
Veerendrababu Vakkapatla, Shariq Faraz, Virendra Singh
Browse the full ICAART paper archive.
Veerendrababu Vakkapatla, Shariq Faraz, Virendra Singh
Browse the full ICAART paper archive.