Unrewarded bottleneck transitions, called zero-incentive dynamics, cause state-of-the-art subgoal-based RL methods to fail, and learning quality degrades sharply with delay between subgoal completion and reward.
Hindsight experience replay
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Zero-Incentive Dynamics: a look at reward sparsity through the lens of unrewarded subgoals
Unrewarded bottleneck transitions, called zero-incentive dynamics, cause state-of-the-art subgoal-based RL methods to fail, and learning quality degrades sharply with delay between subgoal completion and reward.