Pith. sign in

The Potential of the Return Distribution for Exploration in RL

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

This paper studies the potential of the return distribution for exploration in deterministic reinforcement learning (RL) environments. We study network losses and propagation mechanisms for Gaussian, Categorical and Gaussian mixture distributions. Combined with exploration policies that leverage this return distribution, we solve, for example, a randomized Chain task of length 100, which has not been reported before when learning with neural networks.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

ADDQ: Adaptive Distributional Double Q-Learning

cs.LG · 2025-06-24 · conditional · novelty 6.0

ADDQ uses the sample variance of distributional value estimates to adaptively blend Q-learning and double Q-learning, reducing bias in tabular, Atari, and MuJoCo experiments.

citing papers explorer

Showing 1 of 1 citing paper.

  • ADDQ: Adaptive Distributional Double Q-Learning cs.LG · 2025-06-24 · conditional · none · ref 2019 · internal anchor

    ADDQ uses the sample variance of distributional value estimates to adaptively blend Q-learning and double Q-learning, reducing bias in tabular, Atari, and MuJoCo experiments.