QUOTA: The Quantile Option Architecture for Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL). In QUOTA, decision making is based on quantiles of a value distribution, not only the mean. QUOTA provides a new dimension for exploration via making use of both optimism and pessimism of a value distribution. We demonstrate the performance advantage of QUOTA in both challenging video games and physical robot simulators.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Nov 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 3; 2023: 4.
13 papers.
Sort:
By area:
- 2021Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directionscited by 73
- 2021Tactical Optimism and Pessimism for Deep Reinforcement Learningcited by 55
- 2021DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learningcited by 26
- 2022The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measurecited by 12
- 2021Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observationscited by 11
- 2021Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilizationcited by 7
- 2021Towards Safe, Explainable, and Regulated Autonomous Drivingcited by 7
- 2023Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Controlcited by 5
- 2022Introspective Experience Replay: Look Back When Surprisedcited by 3
- 2023Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterioncited by 3
- 2022Interpretable Stochastic Model Predictive Control using Distributional Reinforced Estimation for Quadrotor Tracking Systemscited by 1
- 2023A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learningcited by 1
1 more
- 2023Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion25 Oct 2023
- 2023DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaption8 Oct 2023
- 2023A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning4 Jun 2023
- 2023Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control22 Feb 2023
- 2022Introspective Experience Replay: Look Back When Surprised7 Jun 2022
- 2022The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure20 May 2022
- 2022Interpretable Stochastic Model Predictive Control using Distributional Reinforced Estimation for Quadrotor Tracking Systems14 May 2022
- 2021Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions21 Dec 2021
- 2021Towards Safe, Explainable, and Regulated Autonomous Driving20 Nov 2021
- 2021Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization17 Oct 2021
- 2021Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations17 Sep 2021
- 2021DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning16 Feb 2021
1 more
- 2021Tactical Optimism and Pessimism for Deep Reinforcement Learningcited by 55
- 2021DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learningcited by 26
- 2022The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measurecited by 12
- 2021Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observationscited by 11
- 2021Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilizationcited by 7
- 2023Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Controlcited by 5
- 2022Introspective Experience Replay: Look Back When Surprisedcited by 3
- 2023Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterioncited by 3
- 2022Interpretable Stochastic Model Predictive Control using Distributional Reinforced Estimation for Quadrotor Tracking Systemscited by 1
- 2023A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learningcited by 1
- 2023DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaptioncited by 0
- 2023Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion25 Oct 2023
- 2023DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaption8 Oct 2023
- 2023A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning4 Jun 2023
- 2023Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control22 Feb 2023
- 2022Introspective Experience Replay: Look Back When Surprised7 Jun 2022
- 2022The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure20 May 2022
- 2022Interpretable Stochastic Model Predictive Control using Distributional Reinforced Estimation for Quadrotor Tracking Systems14 May 2022
- 2021Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization17 Oct 2021
- 2021Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations17 Sep 2021
- 2021DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning16 Feb 2021
- 2021Tactical Optimism and Pessimism for Deep Reinforcement Learning7 Feb 2021