mlsanityData to 7 Oct 2026

Knowledge-Guided Exploration in Deep Reinforcement Learning

arXiv 2210.15670 ↗First posted 26 Oct 2022cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP). Two types of permissibility are defined under SAP. The first type says that after an action at is performed in a state st and the agent has reached the new state st+1, the agent can decide whether at is permissible or not permissible in st. The second type says that even without performing at in st, the agent can already decide whether at is permissible or not in st. An action is not permissible in a state if the action can never lead to an optimal solution and thus should not be tried (over and over again). We incorporate the proposed SAP property and encode action permissibility knowledge into two state-of-the-art deep RL algorithms to guide their state-action exploration together with a virtual stopping strategy. Results show that the SAP-based guidance can markedly speed up RL training.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 42 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

24 of 42 references.

References · 24

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  5. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  6. 2016The Option-Critic Architecturecited by 433
  7. 2016Learning to reinforcement learncited by 369
  8. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
  9. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 322
  10. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  11. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
  12. 2018Safe Exploration in Continuous Action Spacescited by 237
12 more
  1. 2013(More) Efficient Reinforcement Learning via Posterior Samplingcited by 233
  2. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
  3. 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 99
  4. 2018Learn What Not to Learn: Action Elimination with Deep Reinforcement Learningcited by 77
  5. 2018Investigating Human Priors for Playing Video Gamescited by 39
  6. 2017BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systemscited by 30
  7. 2016End-to-End Deep Reinforcement Learning for Lane Keeping Assistcited by 27
  8. 2017What can you do with a rock? Affordance extraction via word embeddingscited by 13
  9. 2013Simulated Car Racing Championship: Competition Software Manualcited by 8
  10. 2017Adaptive Exploration-Exploitation Tradeoff for Opportunistic Banditscited by 8
  11. 2013Concurrent learning-based approximate optimal regulationcited by 5
  12. 2016Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fearcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Modelscited by 4
  2. 2024AUTONODE: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automationcited by 1