arXiv AI
Efficient Exploration Is Enough
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 3
When Do Intrinsic Rewards Lead to Exploration?
The paper investigates when intrinsic rewards effectively drive exploration in reinforcement learning. It introduces a formal criterion that evaluates policies based on the counterfactual information they acquire, comparing how well their histories can replace experience from alternative policies. Using a simple environment, the authors show that common intrinsic reward objectives—count-based, prediction-error, empowerment, and information-gain—can lead to Pareto-suboptimal exploration under this criterion, and they propose conditions and a new objective that better align with optimal exploration.
arXiv AI
Oct 1
ASH: Agents that Self-Hone in Long-Horizon Worlds
arXiv:2605.14211v4 Announce Type: replace Abstract: Long-horizon visuomotor tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrat...
arXiv AI
Jun 19
Can In-Context Learning Support Intrinsic Curiosity?
arXiv:2606. 19476v1 Announce Type: cross Abstract: Effective machine learning depends not only on how we model data, but also on what data we choose to collect.
arXiv Computation and Language
Oct 1
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
arXiv:2609.38334v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-mode...
arXiv AI
Aug 26
Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
arXiv:2507.11482v5 Announce Type: replace Abstract: Artificial learning systems are graduating from passive learners to increasingly autonomous agents, lending pragmatic urgency to the question of wh...
arXiv AI
Jun 9
ASH: Agents that Self-Hone via Embodied Learning
arXiv:2605. 14211v3 Announce Type: replace Abstract: Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales.