Research map / Reinforcement learning / Visual and representation RL

Meta-Reinforcement Learning with Zero-Shot Reinforcement Learning

NeurIPS 2026 · Reinforcement learning › Visual and representation RL · approach: Task-inference meta-RL

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Combines meta-RL with zero-shot RL from behavior foundation models, using reward-free pretraining to reduce the need for hand-built training task distributions.

Problem

Meta-RL agents need diverse training sets of environments and reward functions, which are expensive to construct; BFMs enable zero-shot RL but the abstract is truncated before stating its limitation in detail.

Approach

Uses behavior foundation models learned from reward-free data as the basis for meta-RL, so that task diversity comes from reward-free pretraining rather than hand-constructed task sets. Only the abstract is available, so details are limited.

Limitations

• Only the truncated abstract is available; full method and results are unknown

Experimental setup

Builds on: behavior foundation models

Closest papers by meaning

• MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components (AAAI 2024 · similarity 0.90)
• MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning (ICLR 2024 · similarity 0.90)
• DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
• Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity (NeurIPS 2024 · similarity 0.90)
• Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills (AAAI 2024 · similarity 0.89)
• First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs (NeurIPS 2024 · similarity 0.89)