Faynt is a family of Transformer policies (10M and 75M parameters) that control all 26 characters in Super Smash Bros. Melee from a single checkpoint. After reinforcement learning, the 10M model wins 98.4% of same‑character games against fourteen specialist and multi‑character releases, and defeats a zero‑delay Slippi‑AI model in all 68 evaluated games. The work details architecture, scaling, hyperparameter transfer, supervised pretraining on 840,000 human replays, post‑training curricula, distillation, and efficient inference, and it releases the weights, benchmark suites, and a platform for automated model tournaments.
arXiv:2607. 00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games.
arXiv:2607. 29577v1 Announce Type: new Abstract: Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reasoning: the ability to choose well when geometry, timing, resources, objectives, and rule interactions all matter at once.
The paper explores a runtime strategy-selection framework where a large language model (LLM) guides a pre‑trained reinforcement learning (RL) policy for non‑player characters (NPCs) in a Unity combat game without altering the underlying policy. Five NPC agents sharing a PPO policy were compared in a baseline setup and an LLM‑augmented setup, where a locally hosted Mistral 7B model assigns one of four tactical tags every five seconds based on live game state. Across 600 episodes against three scripted opponents, the LLM‑augmented agents more than doubled their win rate against a Balanced opponent, improved performance against an Evasive opponent, but struggled against an Aggressive opponent due to over‑reliance on encirclement; analysis of 2,430 strategy selections revealed limited zero‑shot differentiation with the model favoring Surround in 83.8% of cases.
CHAMP is a cross‑domain matchmaking framework for Multiplayer Online Battle Arena games that tackles cold‑start, distribution shift, and data‑scarcity issues by using hybrid player profiles and a Domain‑Aware Win‑rate Network (DAWN). DAWN learns mode‑conditioned representations through a shared network, achieving 67.73% win‑rate prediction accuracy and improving match balance in large‑scale A/B tests. The system reduces imbalanced matches, notably cutting 5‑minute kill crushing rates by up to 20.73% for lower‑tier players.
ShuttleArena is a physics‑based singles badminton self‑play environment that integrates continuous shuttle flight, player interception, structured shot generation, and post‑shot recovery. The policy employs role‑conditioned outputs, allowing interpretable tactical probes through masked interception choices for receivers and factorized hitter actions over shot azimuth, elevation, speed, and recovery target. Evaluation with frozen checkpoints, controlled tactical probes, recovery ablations, qualitative rollouts, and a human‑data sanity check demonstrates competitive performance and reveals that learned recovery behavior is critically important for success.
arXiv:2609.36830v1 Announce Type: new Abstract: Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation wi...
arXiv:2606. 11387v1 Announce Type: cross Abstract: Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets.
arXiv:2608.24479v1 Announce Type: new Abstract: Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, challenging stabilizers designed for...
arXiv:2606. 10389v1 Announce Type: new Abstract: Recent advances in LLM-driven code evolution have enabled automated discovery by iteratively generating and improving programs.
arXiv:2606. 03238v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) makes large-scale post-training possible by replacing an underspecified human objective with learned and scalable proxies.
The paper introduces WebMRE, an offline benchmark comprising 541 tasks and 5,293 steps extracted from WebArena trajectories, designed to provide deterministic scoring for web agents without live environments. It enables the first systematic study of how guide sentences and grounded actions reinforce each other, showing that jointly decoding a guide improves element selection accuracy and that the guide acts as a causal instruction channel. The authors fine‑tune models that outperform leading zero‑shot baselines on all offline metrics.
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.