Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection

• URL: http://arxiv.org/abs/2601.12310v1
• Date: Sun, 18 Jan 2026 08:35:56 GMT
• Title: Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection
• Authors: Jennifer Dodgson, Alfath Daryl Alhajir, Michael Joedhitya, Akira Rafhael Janson Pattirane, Surender Suresh Kumar, Joseph Lim, C. H. Peh, Adith Ramdas, Steven Zhang Zhexu,
• Abstract summary: This paper provides a proof-of-concept system architecture for stable self-training under sparse external feedback and bounded memory.<n>We introduce a self-training architecture in which learning is mediated exclusively by environmental viability, rather than by reward, objective functions, or externally defined fitness criteria.
• Score: 0.27087606206363224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to reward hacking and semantic drift. This paper provides a proof-of-concept system architecture for stable self-training under sparse external feedback and bounded memory, and empirically characterises its learning dynamics and failure modes. We introduce a self-training architecture in which learning is mediated exclusively by environmental viability, rather than by reward, objective functions, or externally defined fitness criteria. Candidate behaviours are executed under real resource constraints, and only those whose environmental effects both persist and preserve the possibility of future interaction are propagated. The environment does not provide semantic feedback, dense rewards, or task-specific supervision; selection operates solely through differential survival of behaviours as world-altering events, making proxy optimisation impossible and rendering reward-hacking evolutionarily unstable. Analysis of semantic dynamics shows that improvement arises primarily through the persistence of effective and repeatable strategies under a regime of consolidation and pruning, a paradigm we refer to as negative-space learning (NSL), and that models develop meta-learning strategies (such as deliberate experimental failure in order to elicit informative error messages) without explicit instruction. This work establishes that environment-grounded selection enables sustainable open-ended self-improvement, offering a viable path toward more robust and generalisable autonomous systems without reliance on human-curated data or complex reward shaping.

Related papers

• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• Balance Equation-based Distributionally Robust Offline Imitation Learning [8.607736795429638]
  Imitation Learning (IL) has proven highly effective for robotic and control tasks where manually designing reward functions or explicit controllers is infeasible.<n>Standard IL methods implicitly assume that the environment dynamics remain fixed between training and deployment.<n>We address this challenge through Balance Equation-based Distributionally Robust Offline Learning.<n>We formulate the problem as a distributionally robust optimization over an uncertainty set of transition models, seeking a policy that minimizes the imitation loss under the worst-case transition distribution.
  arXiv  Detail & Related papers  (2025-11-11T07:48:09Z)
• Environment Agnostic Goal-Conditioning, A Study of Reward-Free Autonomous Learning [0.0]
  We show that an agent can learn to solve tasks by selecting its own goals in an environment-agnostic way.<n>Our method is independent of the underlying off-policy learning algorithm.
  arXiv  Detail & Related papers  (2025-11-06T17:51:11Z)
• Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence [0.11844977816228043]
  We propose a unified cognitive framework that integrates goal reasoning, dynamic task generation, and self-reflective learning into an adaptive architecture.<n>A mathematically grounded theoretical analysis demonstrates that ATM can autonomously evolve from suboptimal to optimal behavior without external supervision.
  arXiv  Detail & Related papers  (2025-11-02T01:13:12Z)
• One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration [77.8436947454471]
  Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program.<n>OneLife is a framework that models world dynamics through conditionally-activated programmatic laws.<n>OneLife can successfully learn key environment dynamics from minimal, unguided interaction.
  arXiv  Detail & Related papers  (2025-10-14T02:49:32Z)
• No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery [53.08822154199948]
  Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks. This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics. We develop a method that directly trains on scenarios with high learnability.
  arXiv  Detail & Related papers  (2024-08-27T14:31:54Z)
• Continuously evolving rewards in an open-ended environment [0.0]
  RULE: Reward Updating through Learning and Expectation is tested in a simplified ecosystem-like setting. The population of entities successfully demonstrate the abandonment of an initially rewarded but ultimately detrimental behaviour. These adjustment happen through endogenous modification of the entities' underlying reward function, during continuous learning, without external intervention.
  arXiv  Detail & Related papers  (2024-05-02T13:07:56Z)
• Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning [12.76337275628074]
  In this work, we propose a variational dynamic model based on the conditional variational inference to model the multimodality andgenerativeity. We derive an upper bound of the negative log-likelihood of the environmental transition and use such an upper bound as the intrinsic reward for exploration. Our method outperforms several state-of-the-art environment model-based exploration approaches.
  arXiv  Detail & Related papers  (2020-10-17T09:54:51Z)
• Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
  empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
  arXiv  Detail & Related papers  (2020-07-14T21:10:16Z)
• Ecological Reinforcement Learning [76.9893572776141]
  We study the kinds of environment properties that can make learning under such conditions easier. understanding how properties of the environment impact the performance of reinforcement learning agents can help us to structure our tasks in ways that make learning tractable.
  arXiv  Detail & Related papers  (2020-06-22T17:55:03Z)
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity [67.24635298387624]
  We show that an off-policy RL algorithm can reason about and tackle lifelong non-stationarity. Our method leverages latent variable models to learn a representation of the environment from current and past experiences. We also introduce several simulation environments that exhibit lifelong non-stationarity, and empirically find that our approach substantially outperforms approaches that do not reason about environment shift.
  arXiv  Detail & Related papers  (2020-06-18T17:34:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.