Ogbench: Benchmarking Offline Goal-conditioned RL

Abstract

Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without rewards. Despite the importance of this setting, we lack a standard benchmark that can systematically evaluate the capabilities of offline GCRL algorithms. In this work, we propose OGBench, a new, high-quality benchmark for algorithms research in offline goal-conditioned RL. OGBench consists of 8 types of environments, 85 datasets, and reference implementations of 6 representative offline GCRL algorithms. We have designed these challenging and realistic environments and datasets to directly probe different capabilities of algorithms, such as stitching, long-horizon reasoning, and the ability to handle high-dimensional inputs and stochasticity. While representative algorithms may rank similarly on prior benchmarks, our experiments reveal sta

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypark2024ogbench

Related papers

• RL Unplugged: A Suite Of Benchmarks For Offline Reinforcement Learning (2020)0.00
• The Generalization Gap In Offline Reinforcement Learning (2023)0.00
• SMORE: Score Models For Offline Goal-conditioned Reinforcement Learning (2023)0.00
• Neorl-2: Near Real-world Benchmarks For Offline Reinforcement Learning With Extended Realistic Scenarios (2025)0.00
• Provably Efficient Offline Goal-conditioned Reinforcement Learning With General Function Approximation And Single-policy Concentrability (2023)0.00
• D4RL: Datasets For Deep Data-driven Reinforcement Learning (2020)0.00
• A Benchmark Environment For Offline Reinforcement Learning In Racing Games (2024)2.26
• Goal-conditioned Data Augmentation For Offline Reinforcement Learning (2024)0.00