d4rl-benchmarks

Tag

#d4rl-benchmarks

Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation

arXiv cs.LG ↗ · 2026-09-18 Cached

The paper proposes RSIQL, a non-hierarchical method for offline goal-conditioned reinforcement learning that uses selective reward stimulation to improve performance on benchmarks like D4RL.

0 favorites 0 likes

← Back to home

d4rl-benchmarks

Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation

Submit Feedback