Information-gain exploration bonuses are claimed to converge and to make model-based exploration sample-efficient, but the central mathematical proof does not hold together.
Then, the function to predict the next state,fs :H→S or fs :H×A→S , can be assigned any GP prior (e.g., SVGP)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
Information-gain exploration bonuses are claimed to converge and to make model-based exploration sample-efficient, but the central mathematical proof does not hold together.