Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL
Hyeonseong Jeon, Youngwoon Lee
Scaling offline goal-conditioned reinforcement learning (GCRL) to long-horizon tasks is difficult because (1) long-range value learning depends on shorter-range estimates that may…
cs.LG2023
DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
Vint Lee, Pieter Abbeel, Youngwoon Lee
Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary t…