Subgoal Discovery for Hierarchical Reinforcement Learning Using Learned Policies

By Sandeep Goel, Manfred Huber. 2003

69 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Sergey Levine
2. Yoshua Bengio
3. Josh Tenenbaum
4. Ruslan Salakhutdinov
5. Abhinav Kumar Gupta
6. Zhe Gan
7. Jianfeng Gao
8. Trevor Darrell

Citations in the corpus

• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation (2016, background): “In the context of hierarchical RL, Goel and Huber [13] discuss a framework for subgoal discovery using the structural aspects of a learned policy model.”
• Deep Successor Reinforcement Learning (2016, methodology): “In the context of hierarchical RL, [8] discuss a framework for subgoal extraction using the structural aspects of a learned policy model.”
• A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning (2019, methodology): “More sophisticated methods search for subgoal states to define temporally-extended actions, called options, that explore the state-space more efficiently, [7, 14], use statevisitation counts to encourage the agent to explore states that have”
• Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning (2022, background): “In the context of hierarchical RL, McGovern & Barto (2001); Goel & Huber (2003) tackle exploration for temporally extended actions.”