REVIEW 3 cited by
Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Characterizing aleatoric and epistemic uncertainty on the predicted rewards can help in building reliable reinforcement learning (RL) systems. Aleatoric uncertainty results from the irreducible environment stochasticity leading to inherently risky states and actions. Epistemic uncertainty results from the limited information accumulated during learning to make informed decisions. Characterizing aleatoric and epistemic uncertainty can be used to speed up learning in a training environment, improve generalization to similar testing environments, and flag unfamiliar behavior in anomalous testing environments. In this work, we introduce a framework for disentangling aleatoric and epistemic uncertainty in RL. (1) We first define four desiderata that capture the desired behavior for aleatoric and epistemic uncertainty estimation in RL at both training and testing time. (2) We then present four RL models inspired by supervised learning (i.e. Monte Carlo dropout, ensemble, deep kernel learning models, and evidential networks) to instantiate aleatoric and epistemic uncertainty. Finally, (3) we propose a practical evaluation method to evaluate uncertainty estimation in model-free RL based on detection of out-of-distribution environments and generalization to perturbed environments. We present theoretical and experimental evidence to validate that carefully equipping model-free RL agents with supervised learning uncertainty methods can fulfill our desiderata.
Forward citations
Cited by 3 Pith papers
-
Auditing the Risk Claims of Distributional Reinforcement Learning
40-95% of the strongest risk trade-off claims of QR-DQN, C51 and IQN are refuted; the learned risk is a training artifact, not real environment stochasticity.
-
Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation
UARL gates policy deployment on ensemble critic variance computed on a target-domain dataset, iteratively expanding domain randomization until the uncertainty threshold is met.
-
Uncertainty Prioritized Experience Replay
UPER uses ensemble-based epistemic and aleatoric uncertainty to compute an information gain priority for experience replay, outperforming TD-error prioritization on Atari-57.
Discussion (0). Sign in to comment.