Data to 14 Oct 2026

Meta-World+: An Improved, Standardized, RL Benchmark

arXiv 2505.11289 ↗First posted 16 May 2025cs.AI cs.LGcited by 43

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which inhibit a fair comparison of algorithms. This work strives to disambiguate these results from the literature, while also leveraging the past versions of Meta-World to provide insights into multi-task and meta-reinforcement learning benchmark design. Through this process we release a new open-source version of Meta-World (https://github.com/Farama-Foundation/Metaworld/) that has full reproducibility of past results, is more technically ergonomic, and gives users more control over the tasks that are included in a task set.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 24 of its 42 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

24 of 42 references.

Closest ancestors · 2

Same direction, newest first

Other references · 22

2017Proximal Policy Optimization Algorithmscited by 15,215
2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
2015Trust Region Policy Optimizationcited by 2,580
2020Gradient Surgery for Multi-Task Learningcited by 1,256
2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 253
2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 229

10 more

2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
2020Multi-Task Reinforcement Learning with Soft Modularizationcited by 143
2018Multi-task Deep Reinforcement Learning with PopArtcited by 141
2023A Tutorial on Meta-Reinforcement Learningcited by 108
2023XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAXcited by 55
2023Multi-Task Reinforcement Learning with Mixture of Orthogonal Expertscited by 49
2022PaCo: Parameter-Compositional Multi-Task Reinforcement Learningcited by 46
2024One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotioncited by 43
2021Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentscited by 36
2023Investigating the role of model-based learning in exploration and transfercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 34.

43 papers.

Sort:

By area:

2025RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Modelscited by 28
2025π_textttRL: Online RL Fine-tuning for Flow-based Vision-Language-Action Modelscited by 16
2026One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policycited by 6
2025ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learningcited by 5
2026Stable Deep Reinforcement Learning via Isotropic Gaussian Representationscited by 5
2026Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Controlcited by 5
2025Trajectory Conditioned Cross-embodiment Skill Transfercited by 3
2026Continual Policy Consolidation for Lifelong Robot Learningcited by 3
2026ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Modelscited by 3
2026Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RLcited by 2
2026Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulationcited by 2
2026Rewarding DINO: Predicting Dense Rewards with Vision Foundation Modelscited by 2

31 more

2026Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learningcited by 2
2026VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Modelscited by 2
2026PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Modelscited by 2
2025Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learningcited by 1
2026ForeDiffusion: Foresight-Conditioned Diffusion Policy via Future View Construction for Robot Manipulationcited by 1
2026ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstrationcited by 1
2026Stage-Transition Dense Reward Modeling for Reinforcement Learningcited by 1
2026Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learningcited by 1
2026DLAM: Distributional Latent Actions with Temporal Constraintscited by 1
2026GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Modelcited by 1
2025Quantifying Generalisation in Imitation Learningcited by 0
2025Context Representation via Action-Free Transformer encoder-decoder for Meta Reinforcement Learningcited by 0
2025Sceniris: A Fast Procedural Scene Generation Frameworkcited by 0
2025Meta-RL with Bayesian Linear Task Modelscited by 0
2026Recovering Hidden Reward in Diffusion-Based Policiescited by 0
2026HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactionscited by 0
2026TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancingcited by 0
2026Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Samplingcited by 0
2026Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planningcited by 0
2026Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learningcited by 0
2026A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learningcited by 0
2026Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitionscited by 0
2026A Model-Driven Approach for Developing Families of Reinforcement Learning Environmentscited by 0
2026Rank-Then-Act: Reward-Free Control from Frame-Order Progresscited by 0
2026Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learningcited by 0
2026Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inferencecited by 0
2026Beyond Pairwise Feedback: Listwise Vision-Language Supervision for Preference-Based Reward Learningcited by 0
2026Scalable In-Context Reinforcement Learning with Recurrent Algorithm Distillationcited by 0
2026Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Controlcited by 0
2026Adaptive Mean Flow for Responsive Closed-Loop Robot Controlcited by 0
2026Disentangling Task-Relevant Latent Dynamics for Reward Modelingcited by 0

Similar, not cited

Close in wording, no citation either way