{"ID":2883426,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09325","arxiv_id":"2508.09325","title":"SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens","abstract":"Visual reinforcement learning policies trained on pixel observations often struggle to generalize when visual conditions change at test time. Object-centric representations are a promising alternative, but most approaches use fixed-size slot representations, require image reconstruction, or need auxiliary losses to learn object decompositions. As a result, it remains unclear how to learn RL policies directly from object-level inputs without these constraints. We propose SegDAC, a Segmentation-Driven Actor-Critic that operates on a variable-length set of object token embeddings. At each timestep, text-grounded segmentation produces object masks from which spatially aware token embeddings are extracted. A transformer-based actor-critic processes these dynamic tokens, using segment positional encoding to preserve spatial information across objects. We ablate these design choices and show that both segment positional encoding and variable-length processing are individually necessary for strong performance. We evaluate SegDAC on 8 ManiSkill3 manipulation tasks under 12 visual perturbation types across 3 difficulty levels. SegDAC improves over prior visual generalization methods by 15% on easy, 66% on medium, and 88% on the hardest settings. SegDAC matches the sample efficiency of the state-of-the-art visual RL methods while achieving improved generalization under visual changes. Project Page: https://segdac.github.io/","short_abstract":"Visual reinforcement learning policies trained on pixel observations often struggle to generalize when visual conditions change at test time. Object-centric representations are a promising alternative, but most approaches use fixed-size slot representations, require image reconstruction, or need auxiliary losses to lea...","url_abs":"https://arxiv.org/abs/2508.09325","url_pdf":"https://arxiv.org/pdf/2508.09325v4","authors":"[\"Alexandre Brown\",\"Glen Berseth\"]","published":"2025-08-12T20:16:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\",\"cs.RO\"]","methods":"[\"Reinforcement Learning\",\"Transformer\"]","has_code":false}