Pith. sign in

REVIEW 2 cited by

The Generalization Gap in Offline Reinforcement Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.05742 v2 pith:WCW5TLDK submitted 2023-12-10 cs.LG cs.AI

classification cs.LGcs.AI
keywords learningofflinealgorithmsenvironmentsgeneralizationonlinebehavioralcloning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online reinforcement learning (RL), offline RL, sequence modeling, and behavioral cloning. Our experiments show that offline learning algorithms perform worse on new environments than online learning ones. We also introduce the first benchmark for evaluating generalization in offline learning, collecting datasets of varying sizes and skill-levels from Procgen (2D video games) and WebShop (e-commerce websites). The datasets contain trajectories for a limited number of game levels or natural language instructions and at test time, the agent has to generalize to new levels or instructions. Our experiments reveal that existing offline learning algorithms struggle to match the performance of online RL on both train and test environments. Behavioral cloning is a strong baseline, outperforming state-of-the-art offline RL and sequence modeling approaches when trained on data from multiple environments and tested on new ones. Finally, we find that increasing the diversity of the data, rather than its size, improves performance on new environments for all offline learning algorithms. Our study demonstrates the limited generalization of current offline learning algorithms highlighting the need for more research in this area.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Improving greenhouse fruit-production control by integrating reinforcement learning into short-horizon model predictive control

    math.OC 2026-07 conditional novelty 5.5 of 10

    Trajectory-selection RL–MPC with a 1-hour horizon matches specialist RL and beats same-horizon MPC on GreenLight tomato control, improving 54% over generalist RL and 80% over MPC on 25 held-out weather days.

  2. Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details

    cs.AI 2026-08 conditional novelty 5.0 of 10

    For Other-Play in Yokai, agents trained with different implementation details coordinate across implementations about as well as across seeds, supporting inter-seed cross-play as a proxy for cross-implementation evaluation.

Pith tools