Unsupervised Learning Of Efficient Exploration: Pre-training Adaptive Policies Via Self-imposed Goals

Abstract

Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks. A promising direction, grounded in human development, investigates agents that learn by setting and pursuing their own goals. The core challenge lies in how to effectively generate, select, and learn from such goals. Our focus is on broad distributions of downstream tasks where solving every task zero-shot is infeasible. Such settings naturally arise when the target tasks lie outside of the pre-training distribution or when their identities are unknown to the agent. In this work, we (i) optimize for efficient multi-episode exploration and adaptation within a meta-learning framework, and (ii) guide the training curriculum with evolving estimates of the agent's post-adaptation performance. We present ULEE, an unsupervised meta-learning method that combines an in-context learner with an adversarial goal-generation strategy that maintains training at the front

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypappalardo2026unsupervised

Related papers

• Never Give Up: Learning Directed Exploration Strategies (2020)0.00
• Learning With Amigo: Adversarially Motivated Intrinsic Goals (2020)0.00
• Learning More Skills Through Optimistic Exploration (2021)0.00
• Self-supervised Goal-reaching Results In Multi-agent Cooperation And Exploration (2025)0.00
• Learn The Ropes, Then Trust The Wins: Self-imitation With Progressive Exploration For Agentic Reinforcement Learning (2025)0.00
• First-explore, Then Exploit: Meta-learning To Solve Hard Exploration-exploitation Trade-offs (2023)0.00
• Maximum Entropy Gain Exploration For Long Horizon Multi-goal Reinforcement Learning (2020)0.00
• Generating Automatic Curricula Via Self-supervised Active Domain Randomization (2020)0.00