← Back to all news
arXiv Machine Learning By Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu

Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals

Read the original on arXiv Machine Learning →

The paper introduces Safe Contrastive Reinforcement Learning (Safe-CRL), a method that corrects bias in contrastive RL caused by failure-terminated Markov decision processes. By applying mass-weighted InfoNCE and a log-survival-mass score, Safe-CRL uses only a one-bit failure signal to improve survival and goal-reaching performance across twelve robot navigation and locomotion tasks. The approach demonstrates complex failure-avoidance behaviors and completes the theoretical foundation of contrastive RL under failure termination.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 21

Survival Reinforcement Learning: Toward Scalable Self-Supervised RL

The paper introduces Survival Reinforcement Learning (SRL), an online classification-based method that extends the survival value learning framework to maximize an agent’s dwell time at target goals. SRL addresses limitations of contrastive reinforcement learning (CRL) in long-horizon, goal-conditioned tasks by avoiding the uniformity-tolerance dilemma and reducing undesirable bang-bang control behaviors. Across robotic benchmarks, SRL matches CRL on manipulation tasks and outperforms it by 2x to 8x on stable, long-horizon locomotion tasks, suggesting classification-based approaches are a promising direction for scaling reinforcement learning.

By Franki Nguimatsia-Tiofack, Fabian Schramm, Th\'eotime Le Hellard, Justin Carpentier
agentsreinforcement-learningroboticsbenchmarks
More like this →
arXiv Machine Learning
Jul 13

SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions

arXiv:2607. 08925v1 Announce Type: new Abstract: Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do.

By Elham Daneshmand, Majid Khadiv, Glen Berseth, Hsiu-Chin Lin
agentsreinforcement-learningroboticsbenchmarkssafety
More like this →