mlsanityData to 14 Oct 2026

IRumAI: Reinforcement Learning for Indian Rummy

arXiv 2606.21975 ↗First posted 20 Jun 2026cs.AI cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Despite its massive player base and complex hidden-information dynamics, Indian Rummy has received no reinforcement learning attention. Existing agents rely on combinatorial search, which is tactically strong but slow at inference. We present IRumAI, the first RL agent for the domain. IRumAI integrates Proximal Policy Optimization (PPO), meld-aware observation encoding, deadwood-driven reward shaping, and a dual-branch convolutional architecture. IRumAI is RL-trained solely against weak heuristics, after a one-time behaviour-cloning warm-start on stronger demonstration data. It generalises to defeat the entire baseline hierarchy, including a 53.9% win rate against the strongest search-based opponent unseen during RL training. Bypassing explicit search, IRumAI requires just 0.33 ms per action, which is over 7,000x faster than the state-of-the-art heuristic. Ablations validate our architectural choices, and linear probing reveals that the network implicitly models the opponent's hidden hand from public interactions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 14 references that are in the map. First posted on arXiv 20 Jun 2026.

Builds on

6 of 14 references.

References · 6

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  3. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 233
  4. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  5. 2021DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learningcited by 66
  6. 2025Quantitative Rule-Based Strategy modeling in Classic Indian Rummy: A Metric Optimization Approachcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AT2PO: Agentic Turn-based Policy Optimization via Tree Search
  2. 2026FARL: A Fully Automated Pipeline of RL Interface and Solver Design
  3. 2026A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong
  4. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
  5. 2024Scalable Reinforcement Learning-based Neural Architecture Search
  6. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
  7. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
  8. 2026From Imitation to Interaction: Mastering Game of Schnapsen with Shallow Reinforcement Learning