arXiv Machine Learning
The Predictive--Optimization Gap in GuanDan Self-Play
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
Jul 10
Beyond Success Rates: Trainability and Extractability for Offline GCRL
arXiv:2602. 05459v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) is typically benchmarked by the best tuned success rate of each method.
arXiv AI
Jun 2
MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution
arXiv:2606. 00017v1 Announce Type: new Abstract: Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players.
arXiv AI
1d ago
VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching
arXiv:2610.27280v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based meth...
arXiv AI
Jun 30
Self-Play Reinforcement Learning under Imperfect Information in Big 2
arXiv:2605. 28863v2 Announce Type: replace-cross Abstract: Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents.
arXiv AI
Oct 5
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
Prospective Hindsight (PH) is a self‑calibrating training principle for reinforcement learning that augments any retrospective base method with a signal derived from the gap between an agent’s prospective prediction and its retrospective evaluation. By weighting gradients with a stop‑gradient surprise based on this prediction‑reality gap, PH highlights samples where the agent’s self‑model is most inaccurate and encourages the policy and predictor to co‑evolve, progressively focusing on remaining blind spots. Experiments on single‑turn verifiable tasks and a multi‑turn personal‑agent task show that PH improves both task performance and calibration across model scales, addressing overconfident failures in single‑turn settings and underconfident successes in multi‑turn settings.
arXiv AI
Jul 21
CIGPO: Contextual Information-Gain Policy Optimization for Multi-Turn Evidence-Reading LLM Agents
arXiv:2607. 16244v1 Announce Type: cross Abstract: Training multi-turn evidence-reading agents with outcome-only reinforcement learning is unstable because intermediate turns receive little direct credit.