Meta-World

A benchmark of 50 robotic manipulation tasks for multi-task and meta-reinforcement learning.

Papers using Meta-World (62)

UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning2026LaGO: Latent Action Guidance for Online Reinforcement Learning2026When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?2026Policy Learning from Large Vision-Language Model Feedback without Reward Modeling2025 · 1 citesSPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning2026Revisiting Mixture Policies in Entropy-Regularized Actor-Critic2026One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning2026TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing2026GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control2026MVR: Multi-view Video Reward Shaping for Reinforcement Learning2026SEAR: Sample Efficient Action Chunking Reinforcement Learning2026Contextual Latent World Models for Offline Meta Reinforcement Learning2026ProgAgent:A Continual RL Agent with Progress-Aware Rewards2026Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models2026R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation2026Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics2026MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models2026Task-Aware Exploration via a Predictive Bisimulation Metric2026Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning2026Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback2026Continual Policy Distillation from Distributed Reinforcement Learning Teachers2026Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning2025Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation2025Soft Conflict-Resolution Decision Transformer for Offline Multi-Task Reinforcement Learning2025Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks2025In-Context Policy Adaptation via Cross-Domain Skill Diffusion2025Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning2025Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning2025Residual Reward Models for Preference-based Reinforcement Learning2025Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning2025VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models2025Meta-World+: An Improved, Standardized, RL Benchmark2025Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning2025Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning2025Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision2025Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks2025Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning2025Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks2025Model Evolution Framework with Genetic Algorithm for Multi-Task Reinforcement Learning2025Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning2025Subtask-Aware Visual Reward Learning from Segmented Demonstrations2025Effective Exploration Based on the Structural Information Principles2024 · 3 citesA Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning2024 · 2 citesMeta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement2024 · 2 citesReset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning2024 · 1 citesBigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control2024 · 1 citesFuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning2024 · 1 citesCentralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning2024 · 1 citesGeneralizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization2024 · 1 citesState Chrono Representation for Enhancing Generalization in Reinforcement Learning2024 · 1 citesHierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery2024 · 1 citesHindsight PRIORs for Reward Learning from Human Preferences2024OMPO: A Unified Framework for RL under Policy and Dynamics Shifts2024Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement Learning2024Text-Aware Diffusion for Policy Learning2024Forward KL Regularized Preference Optimization for Aligning Diffusion Policies2024Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner2024Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions2024A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning2024Robot Policy Learning with Temporal Optimal Transport Reward2024Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance2024Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model2024