Research map / Reinforcement learning / Visual and representation RL
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hierarchical goal-conditioned Q-estimators with intrinsic rewards over Q-learning | Q-Learning · Stochastic decision process | average extrinsic reward: 0.01 -> 0.13 | Helped |
| add intrinsic goal-directed hierarchy over flat DQN | DQN · Montezuma's Revenge | score: 0 -> +400 | Helped |
| compare h-DQN against Gorila DQN | Gorila DQN · Montezuma's Revenge | score: 4.16 -> +400 | Helped |
| two-phase training: pre-train controller with meta-controller epsilon 1, then joint training | h-DQN · Montezuma's Revenge | reward: 2.3 million pre-train steps, then 2 million joint steps | Helped |
Closest papers by meaning
- Language as an Abstraction for Hierarchical Deep Reinforcement Learning (NeurIPS 2019 · similarity 0.90)
- Stochastic Neural Networks for Hierarchical Reinforcement Learning (ICLR 2017 · similarity 0.88)
- Hierarchical Imitation and Reinforcement Learning (ICML 2018 · similarity 0.87)
- Sample Complexity of Goal-Conditioned Hierarchical Reinforcement Learning (NeurIPS 2023 · similarity 0.86)
- Deep Reinforcement Learning from Hierarchical Preference Design (ICML 2025 · similarity 0.86)
- Reconciling Spatial and Temporal Abstractions for Goal Representation (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.