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.
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 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ADDQ: Adaptive Distributional Double Q-Learning
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.