×
We propose a slowness objective to effectively learn the subgoal representation for goal-conditioned hierarchical reinforcement learning.
Active Hierarchical Exploration with Stable Subgoal Representation Learning. ... Learning Subgoal Representations with Slow Dynamics. ICLR 2021. [c8]. view.
Learning subgoal representations with slow dynamics. S Li, L Zheng, J Wang, C Zhang. International Conference on Learning Representations, 2021. 51, 2021 ...
Jun 24, 2024 · In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach.
Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration · Learning Subgoal Representations with Slow Dynamics.
Apr 17, 2024 · Selecting reasonable subgoals that capture the task's semantics provides meaning- ful guidance to low-level policy learning. Pre-defined subgoal.
Goal-conditioned hierarchical reinforcement learning (HRL) has shown promising results for solving complex and long-horizon RL tasks.
Multi-agent reinforcement learning (MARL) effectively improves the learning speed of agents in sparse reward tasks with the guide of subgoals.
Jun 24, 2024 · In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach.