An agent that plans on a landmark graph built from a locally accurate value function reaches long-range goals faster and more reliably than model-free baselines in sparse-reward environments.
Hierarchical Reinforcement Learning with Hindsight
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functions and hindsight learning, allowing agents to learn policies belonging to different time scales in parallel. We show that our method significantly accelerates learning in a variety of discrete and continuous tasks.
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mapping State Space using Landmarks for Universal Goal Reaching
An agent that plans on a landmark graph built from a locally accurate value function reaches long-range goals faster and more reliably than model-free baselines in sparse-reward environments.