Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners

The dominance of Neural Networks (NNs) in RL is partially due to their incremental learning capability, which naturally suits the online, non-stationary nature of self-play training. However, gradient-boosted trees like LightGBM are widely recognised as the state of the art for tabular data in supervised learning, often outperforming NNs in accuracy and efficiency. Game states are inherently tabular---discrete actions, categorical card identities, structured board positions---which makes them an ideal candidate for tree-based methods. We introduce LUGL (Local Updates, Global Learning), a framework that decouples data collection from model fitting, enabling non-incremental learners such as GBTs to operate in RL settings where they would otherwise fail due to distributional shift. LUGL alternates between a local updates phase, where the agent plays self-play games and accumulates tabular updates (Q-values, V-values, policies, or regret values) in a finite table, and a global learning phase, where the table is used to train a function approximator that generalises to unseen states before the table is reset. We test our approach in four standard perfect-information games (Tic-tac-toe, Connect-4, Othello, and Hex) and five imperfect-information games (Kuhn's poker, Leduc Hold'em, Liar's Dice, Goofspiel, and Flop5 Hold'em), and show that our results are competitive with or superior to DQN and DeepCFR. Our experiments demonstrate that the community's strong bias towards NNs in game-playing may be unwarranted, since LightGBM-based agents achieve competitive or superior performance across all tested benchmarks.

Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess

Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc0) released Chessformer, distills the visit counts of an AlphaZero-style Monte Carlo Tree Search (MCTS). Imitating a search is a poor proxy for playing without one, so we fine-tune for single-pass strength with self-play reinforcement learning (RL). Its exploration is usually supplied by an entropy bonus, the reverse Kullback-Leibler (KL) divergence to uniform. We replace it with a forward, mass-covering KL toward the network's own MCTS prior (prior-directed exploration), so exploration covers the moves the prior judges promising, and pair it with an entropy-adaptive sampling temperature, set by the value head's outcome uncertainty, that sharpens once a position is decided. In about two thousand steps it raises puzzle accuracy from 93.9% to 94.9% on a 100,000-puzzle suite and mate-in-four accuracy from 77% to 81% while holding searchless strength at or slightly above the base. Measuring tactical accuracy and playing strength together across a matched-compute sweep, we find the two dissociate: accuracy gains fall in a one-point band while ratings straddle the base, and a control fine-tuned on puzzles alone posts the study's largest tactical gains while shedding roughly 260 Elo; a better puzzle-solver is not thereby a stronger player. Distribution-level measurements show what anchoring buys: without a regularizer self-play collapses onto a single line of play, and the puzzles newly solved are the near misses whose winning move the prior kept alive. The forward-KL prior tops the rating ladder, statistically tied with a reverse-KL anchor that concentrates twice as hard and drops the hardest solutions the mass-covering prior keeps in support.

ShuttleArena: Interpretable Self-Play in Physics-Based Badminton

Badminton is a compact but challenging domain for game AI: a player must choose a physically feasible shuttle trajectory, anticipate the opponent's interception, and recover to a court position whose value depends on the opponent's next response. The central challenge is that shot selection and recovery are not separable: the best recovery depends on the shot-induced opponent response, while the value of the shot depends on whether the hitter can cover the reply. This paper presents ShuttleArena, a physics-based singles badminton self-play environment that couples continuous shuttle flight, player interception, structured shot generation, and post-shot recovery. The policy uses role-conditioned outputs: a masked interception choice on receiver turns and a factorized hitter action over shot azimuth, shot elevation, shot speed, and recovery target, enabling interpretable tactical probes. Episodes are single rallies rather than full scored games, and training uses Proximal Policy Optimization (PPO) self-play against a staged checkpoint opponent pool with sparse terminal rally-outcome rewards and a factor-specific recovery update. Evaluation with frozen checkpoint play, controlled tactical probes, recovery ablations, qualitative rollouts, and a human-data sanity check shows competitive improvement together with interpretable opponent-conditioned changes in shot geometry and recovery behavior. The learned policies produce recognizable badminton-like structure while also reflecting the abstractions of the simulator, and the recovery intervention shows that learned recovery behavior is competitively important. These results suggest that physics-based racket sports are a useful testbed for interactive digital entertainment AI because they require agents to coordinate execution, positioning, and opponent-relative tactical value.

The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning

Reinforcement learning with verifiable rewards has become the dominant recipe for improving large language model reasoning, yet it presumes large human-curated task collections. Zero-data self-play removes this dependency, but existing methods vet learnability only by probing candidates and rejecting post hoc, never learning where along an environment's difficulty axis to place a task, and credit the solver with sparse terminal rewards alone. We recast zero-data self-play as a pursuit-evasion game: in LURE, an LLM evader positions tasks along each environment's difficulty axis to stay one step ahead of a planner-executor pursuer that hunts it down through verifiable interaction. The evader is trained on a capture-frontier reward that peaks when the solver captures it on exactly half of its rollouts, turning barely catchable into a learned positioning strategy rather than a hand-tuned rejection band. The pursuer earns capture-anchored dense process credit, in which monotone verifier progress is group-normalized jointly with the terminal capture under a round-anchored KL that keeps the co-evolution stable. Across three verifiable reasoning environments and three backbone families, LURE outperforms advanced baselines under unified/specialist settings, while the unified model attains stronger aggregate OOD zero-shot accuracy than all trained baselines across nine held-out benchmarks from three task families.

PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search

We revisit Tesauro's TD-Gammon for backgammon money games in the setting of no evaluation-time search. Both checker play and cube action (use of the doubling cube) are learned from scratch via self-play reinforcement learning (RL), with minimal hand-coded logic and no expert features. In this setting, we demonstrate that pure self-play RL suffices to train models that reach near-state-of-the-art playing strength. Specifically, for cubeful money games, our search-free model evaluates faster and is substantially stronger than the open-source engines GNU Backgammon and Open Sage running a one-move (1-ply) look-ahead search.

AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision

AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play $+$ MCTS pipeline, we compare vanilla AlphaZero, a multi-frame variant (limited to Chomp), and an AlphaZero Auxiliary Loss (AZAL) that adds oracle-derived policy supervision. We find that vanilla AlphaZero achieves strong play across both domains but cannot preserve the exact trajectories required for optimal play: in Connect Four, it fails to maintain the optimal line of play, while in Chomp, it fails to consistently restore the $g=0$ invariant. On rectangular Chomp boards, multi-frame inputs alone do not remove this gap. Nevertheless, AZAL substantially improves oracle consistency across multi-seeded full-game traces and sampled-state evaluations. On Chomp, AZAL reaches perfect full-game oracle consistency on 10x11 and high but not complete consistency on 9x10; on Connect Four, AZAL improves oracle-match rate and delays the first oracle mistake, but does not reach perfect play.

A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong

Reinforcement learning agents for imperfect-information card games are only as strong as the opponents they train against, and they are hard to grade, since they beat a random opponent over 99 percent of the time and only tie copies of themselves. So we build a strong, fixed, rule-based expert for Gin Rummy and use it only as a yardstick, never for training. It beats every agent we trained 70 to 99 percent of the time. Across more than a hundred runs, we isolate what makes a lightweight agent stronger. Trust region updates, a well-aimed reward, a curriculum of tougher opponents, warm starting, and keeping the best checkpoint all help, and stacking them lifts a self-play champion from about 30 to 36 percent against the expert. Several ideas did not pay off. Short-term and longer-term reward shaping, learned state embeddings, imitation and DAgger, and a live large language model opponent were each unhelpful, too slow, or too heavy to train at scale. Comparing MLP, convolutional, set-based, attention, and recurrent encoders shows that extra capacity does little to break the ceiling, suggesting the limit is information rather than network size. We add standard baselines (neural fictitious self-play and information set Monte Carlo search) and confirm the approach carries over to Leduc Hold'em, where the optimum is computable. The result is a lightweight, game-agnostic recipe that trains competitive agents without training on the expert, for any game a small model can handle, reported with robust statistics and released as a reusable package.

EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can match or exceed specialized game-theoretic algorithms for solving two-player zero-sum imperfect-information games. The uniform distribution has emerged as a strong policy regularization target for this purpose, but it regularizes equally toward all actions regardless of their viability. We introduce EMAgnet, which instead regularizes toward an exponential moving average (EMA) of the last-iterate policy's parameters, providing an adaptive regularization target that evolves with the agent's improving strategy. We evaluate EMAgnet on both standard two-player zero-sum benchmarks and modified benchmarks with exploration challenges and large numbers of strictly dominated strategies. Relative to PPO self-play with uniform-magnet regularization under both linear and power-law annealing schedules, EMAgnet achieves lower exploitability in the majority of tested environments, with consistent performance gains across games containing strictly dominated strategies.

Superhuman AI for Generals.io Using Self-Play Reinforcement Learning

We present a superhuman AI agent for Generals.io, a real-time strategy game that requires both long-horizon planning and short-term tactics under strong imperfect information. Trained for four days on 4x NVIDIA H200 GPUs, our agent reaches #1 on the public 1v1 leaderboard of over 5,000 human players, leading the second-ranked player by the same margin that separates second place from 25th, and beats the two top-ranked humans head-to-head with a combined 199-70 record across 269 ladder matches. A key enabler is a JAX-native simulator that reaches tens of millions of frames per second on a single GPU, roughly a 10,000x speedup over the prior simulator. On top of this, we train a vision transformer policy end-to-end by self-play with a policy-gradient loop and sparse win/loss reward, using top-advantage sample filtering and an exponential moving average of the policy parameters. Taken together, our findings highlight what matters, and what does not, once a fast simulator removes the data bottleneck.

GARIP: A Running-Average Moving Reference for Last-Iterate Self-Play in Two-Player Zero-Sum Games

Self-play with naive gradient ascent cycles in two-player zero-sum games: the last iterate orbits the equilibrium. Modern methods restore last-iterate convergence by regularizing toward a reference policy -- MMD a fixed one (reaching only the regularized equilibrium), R-NaD a periodic snapshot (the engine of DeepNash). We study GARIP, which anchors to the running average, and isolate what the choice of reference controls. Our central result is a mechanism: collapse tracks the peak lag of the reference, and among causal convex averages of a fixed mean lag the running average (flat profile, peak $=$ mean) uniquely minimizes that peak, while a snapshot's sawtooth has peak $= 2\times$ mean (a one-line theorem). Two consequences follow. Convergence: we prove local last-iterate convergence at constant anchor strength -- the anchor scales the base map's rotation by $1-β$, crossing the stability boundary and turning a recurrent base into a contraction (global convergence is conjectured at small $β$; we characterize a large-$β$ consensus failure). Robustness: GARIP matches R-NaD's peak performance -- on matrix games, the Coin Game, and the board games Connect Four/Othello, both moving references are far more robust than fixed-magnet and magnet-free baselines -- but is the better hyperparameter default; we report it both ways: over the full grid collapse rates are statistically indistinguishable, yet at conventional parameterizations a matched-mean-lag setting collapses in 0/40 vs 10/40 seeds (a snapshot matches it only by knowing to shorten $K$). The boundaries: an anticipatory (negative-weight) reference does better still on the stale side, and the advantage appears only where naive self-play cycles (five deep self-play loops). All experiments are pure JAX and reproducible.

WallZero: Mastering the Game of WallGo with Strategic Analysis

WallGo is a recently introduced strategic board game popularized by the 2025 Netflix series The Devil's Plan. Although played on a small 7 x 7 board, its combination of stone movement and wall placement yields high game-tree complexity and intricate strategic interactions. Despite its growing popularity, WallGo remains underexplored. This paper presents WallZero, an AlphaZero-based agent for the two-player WallGo setting. We introduce tailored action and feature designs to improve playing performance significantly. In the evaluation, WallZero defeats two professional Go players who participated in this study, securing on average 1.98x more territory per game. Beyond its strength, we use WallZero to assess game fairness and identify key strategies for mastering WallGo. Interestingly, our results show that the opening used in the Netflix series yields a more balanced game. Our code is available at https://rlg.iis.sinica.edu.tw/papers/wallzero.

Discovering Lattice Reduction Strategies via Self-Play

The Lenstra-Lenstra-Lovász (LLL) algorithm is a seminal contribution to computer science used for lattice basis reduction, yet its polynomial-time outputs produce bases that are far from optimal as the dimension grows. We show that deep reinforcement learning can discover strictly superior, generalizable reduction strategies by interacting with the primitive action space of LLL. We formulate lattice reduction as a single-player Markov Decision Process (MDP) and train a deep residual network using an AlphaZero-style self-play pipeline augmented with adaptive-horizon MCTS (Monte Carlo Tree Search), which couples multi-step network predictions with an entropy-gated expansion mechanism. The resulting policy, DeltaStar, is trained exclusively on small $8$-dimensional $q$-ary lattices and requires fewer primitive row operations than LLL. Crucially, it generalizes zero-shot to unseen moduli and higher dimensions up to $n=32$ without retraining.

Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL

Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning gains, but collapse and instability are widely observed and poorly understood. The dominant response treats this as a reward-design problem. We argue instead that self-play stability is governed by two distinct levers: a data-level gate that decides which proposer-generated tasks enter the training pool, and the reward signal that updates the policy on tasks already admitted. Through controlled experiments on a Python output-prediction task and a deterministic-DSL twin task that strips pretraining priors, output ambiguity, and executor noise, we find the two levers are asymmetric. A strict gate is sufficient for stability under every reward variant we test, including a self-consistency reward with no access to ground truth; while no reward variant is sufficient once the gate is removed. This asymmetry exposes a counter-intuitive coupling we call the Grounded Proposer Paradox: a proposer with ground-truth access accelerates collapse faster than an ungrounded one when paired with a self-consistency solver, by concentrating training on clean tasks that form the fastest path to a spurious self-consistent attractor. Replacing the binary gate with a continuous strictness parameter $\varepsilon$ further reveals a two-stage phase transition: training-side metrics decouple at low $\varepsilon$, while validation accuracy holds until $\varepsilon$ is much higher. Data-level gating, not reward calibration, is the binding constraint on self-play stability.