arXiv Machine Learning
CFR without Unbiasedness: Debit-Budgeted Public Feedback
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 18
CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedules
arXiv:2608. 14761v1 Announce Type: cross Abstract: At a finite public-chance cut, counterfactual regret minimization (CFR) must choose how many outcomes to evaluate before each regret update.
arXiv Machine Learning
Oct 22
Learning to Allocate Resources with Censored Feedback
The paper addresses an online resource allocation problem where a budget must be distributed among multiple arms under censored feedback. Each arm yields a reward only if it is activated by an unknown Bernoulli process and the allocated budget exceeds a random threshold from an unknown parametric distribution. The authors establish a worst‑case regret lower bound of Σ(√T), propose the RA‑UCB algorithm achieving near‑optimal regret when the budget is known, and introduce MG‑UCB for unknown, round‑dependent budgets, validating both approaches experimentally.
arXiv Machine Learning
Jul 30
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.
arXiv Machine Learning
Aug 11
CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning
arXiv:2608. 07719v1 Announce Type: new Abstract: Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, while naive subsampling can remove rare transitions needed for long-horizon credit assignment.
arXiv Machine Learning
Aug 11
Information Routing across Batch Boundaries: Memory--Batch Tradeoffs in Lipschitz Bandits
arXiv:2608. 07922v1 Announce Type: new Abstract: Adaptive learning needs both a state that preserves what observations imply and opportunities to act on that state.
arXiv AI
Sep 18
Efficient Nash Equilibrium Computation for Cybersecurity Games
The paper introduces Regret-Weighted Payoff Sampling (RWPS), a budgeted estimator that selectively simulates only payoff-matrix cells relevant to a Nash equilibrium and uses a surrogate model for the remaining entries. RWPS provides an instance-dependent error bound weighted by the opponent’s equilibrium mixture and a coverage result guaranteeing that, once the deviation-relevant set is simulated, surrogate error does not affect either player’s regret. Experiments on three 21×21 general-sum games, including an asymmetric Colonel Blotto, show that RWPS achieves four to six times tighter bounds than previous methods and outperforms other sampling strategies on the CyGym and ANSG cyber simulators at low budgets.