OpenAI Blog
Variational option discovery algorithms
Read the original on OpenAI Blog →The Flow has not summarised this story yet — read it at OpenAI Blog.
Related stories
arXiv AI
Sep 30
Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery
arXiv:2609.36473v1 Announce Type: new Abstract: Temporal abstraction via options can improve exploration in large environments. However, existing option discovery algorithms find subgoals that target...
arXiv Machine Learning
4d ago
Mastering Atari 2600 Games with Discovered Options
Wayfarer is a domain‑agnostic, online deep RL agent that discovers options via Laplacian representation learning from high‑dimensional observations and uses them for control. The discovered options improve exploration, accelerate credit assignment, and generalise to unseen settings, leading to faster learning of complex policies. Wayfarer achieves state‑of‑the‑art performance among single‑stream agents on the most challenging Atari 2600 games, especially those requiring long‑horizon exploration such as Montezuma's Revenge and Private Eye.
arXiv AI
Jun 2
MINTS: Minimalist Thompson Sampling
arXiv:2606. 01655v1 Announce Type: cross Abstract: The Bayesian paradigm offers principled tools for sequential decision-making under uncertainty, but its reliance on a probabilistic model for all parameters can hinder the incorporation of complex structural constraints.
arXiv AI
Jul 15
Diversity-Enriched Option-Critic
arXiv:2011. 02565v2 Announce Type: replace-cross Abstract: Temporal abstraction allows reinforcement learning agents to represent knowledge and develop strategies over different temporal scales.
arXiv Machine Learning
Jun 2
Local Preferential Bayesian Optimization
arXiv:2606. 02351v1 Announce Type: new Abstract: Bayesian optimization (BO) is a popular and effective approach for tuning expensive, noisy experiments, but requires the formulation of an explicit objective function.
arXiv Machine Learning
Jul 14
Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data
arXiv:2607. 09817v1 Announce Type: new Abstract: We propose a framework for the Markov chain (MC) choice model with panel data, including parameter estimation, personalized choice prediction, and personalized assortment optimization.