Metraipolis › archive › dc_a359734dfa4f
RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents — arXiv:2611.05601
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05601
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:21:57.202Z
- SHA-256 of the archived text
cddca35c4e3b0951990c725427e7c1139df106435f2674794e9dd242bdf0e959- Stable URL of this page
https://metraipolis.com/documento/dc_a359734dfa4f
How to cite
RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents — arXiv:2611.05601 — arXiv (en), https://arxiv.org/abs/2611.05601 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a359734dfa4f (Metraipolis archive dc_a359734dfa4f, sha256 cddca35c4e3b0951990c725427e7c1139df106435f2674794e9dd242bdf0e959)
BibTeX
@misc{dca359734dfa4f,
title = {RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents — arXiv:2611.05601},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05601},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a359734dfa4f; sha256 cddca35c4e3b0951990c725427e7c1139df106435f2674794e9dd242bdf0e959},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05601. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A deep RL agent trained on a fixed persona reward plays one way: an Explorer keeps exploring while starving, a Survivor hoards on an empty map. Since each persona fixes its own reward, automated playtesting trains N agents for N styles. Changing reward composition mid-episode runs into the switching-stability dilemma: PPO degrades under non-stationary rewards. We present RIDGE, a single-agent architecture that sidesteps the dilemma with two design choices: a state-conditioned blender that computes softmax-normalized sigmoid weights from slow-moving state variables, and a multi-head critic that trains one value head per persona on its own stationary signal. On Crafter with four personas, one \ridge agent acquires both branches of the wood-tier crafting/combat split that no fixed-persona baseline solves jointly, and a sharpness ablation confirms state-conditioning drives the gain. We position these results as demonstrations of the blending mechanism's dynamics across n=3 seeds per condition; larger multi-seed sweeps remain future work. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2611.05601 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:15:49.001Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).