cs.LGSep 3, 2025

Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback

Authors: Zeqiang Zhang, Fabian Wurzberger, Gerrit Schmid, Sebastian Gottwald, Daniel A. Braun

Organizations: Institute of Neural Information Processing, Ulm University, Ulm, Germany

Abstract

Learning from reward functions and imitation learning of demonstrations are the two principal approaches for training autonomous systems that interact with an environment through action and observation. Both, however, require human specification for each behaviour to be acquired, a problem for long-lived self-adaptive systems whose goals and operating conditions cannot be fully anticipated at design time. Recently, Goal-Conditioned Supervised Learning (GCSL) through self-imitation has been proposed as a self-supervised alternative: by strategically relabelling goals, agents can derive policy insights from their own experiences. Despite its successes, this framework presents two notable limitations: (1) learning exclusively from self-generated experiences can exacerbate the agents' inherent biases; (2) the relabelling strategy allows agents to focus solely on successful outcomes, precluding them from learning from their mistakes. To address these issues, we propose GCSL with Negative Feedback (GCSL-NF), which evaluates each trajectory twice: positively with respect to relabelled goals, and correctively with respect to the goal originally intended. The corrective target comes from a similarity function learned contrastively from trajectory-induced neighbourhood relations, so that neither a reward function nor a geometric distance needs to be specified. Our experiments show that GCSL-NF overcomes limitations imposed by agents' initial biases, increasingly benefits from negative feedback as learning progresses, and matches or surpasses GCSL- and HER-based methods. By reducing reliance on prespecified reward functions, the proposed approach is particularly relevant for self-adaptive autonomous systems, where adaptation objectives may be diverse, changing, or difficult to engineer.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Co-Evolving Agents: Learning from Failures as Hard Negatives

    Nov 27, 2025Yeonsung Jung, Trilok Padhi, Sina Shaham +4Hard Negative MiningSelf-Improving Agents

  2. Consistent Zero-Shot Imitation with Contrastive Goal Inference

    Oct 20, 2025Kathryn Wantlin, Chongyi Zheng, Benjamin EysenbachContrastive LearningReinforcement Learning