mlsanityData to 14 Oct 2026

Risk Perspective Exploration in Distributional Reinforcement Learning

arXiv 2206.14170 ↗First posted 28 Jun 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Distributional reinforcement learning demonstrates state-of-the-art performance in continuous and discrete control settings with the features of variance and risk, which can be used to explore. However, the exploration method employing the risk property is hard to find, although numerous exploration methods in Distributional RL employ the variance of return distribution per action. In this paper, we present risk scheduling approaches that explore risk levels and optimistic behaviors from a risk perspective. We demonstrate the performance enhancement of the DMIX algorithm using risk scheduling in a multi-agent setting with comprehensive experiments.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 13 of its 17 references that are in the map. First posted on arXiv 28 Jun 2022.

Builds on

13 of 17 references.

References · 13

  1. 2018Exploration by Random Network Distillationcited by 993
  2. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  3. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  4. 2019The StarCraft Multi-Agent Challengecited by 597
  5. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  6. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  7. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  8. 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 369
  9. 2017Noisy Networks for Explorationcited by 266
  10. 2019Distributional Reinforcement Learning for Efficient Explorationcited by 60
  11. 2021RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agentscited by 31
  12. 2021DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learningcited by 26
1 more
  1. 2021Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learningcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorizationcited by 20
  2. 2023Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterioncited by 3
  3. 2025Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamicscited by 1
  4. 2023DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaptioncited by 0
  5. 2026Distributional Active Inferencecited by 0