Reward function compression facilitates goal-dependent reinforcement learning

• URL: http://arxiv.org/abs/2509.06810v2
• Date: Wed, 10 Sep 2025 17:24:06 GMT
• Title: Reward function compression facilitates goal-dependent reinforcement learning
• Abstract summary: Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner.<n>We propose that goal-dependent learning is initially supported by a capacity-limited working memory system.<n>Our work suggests that efficient goal-directed learning relies on compressing complex goal information into a stable reward function.
• Score: 2.470815298095903
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner. However, this flexibility is cognitively costly, making learning less efficient. Here, we propose that goal-dependent learning is initially supported by a capacity-limited working memory system. With consistent experience, learners create a "compressed" reward function (a simplified rule defining the goal) which is then transferred to long-term memory and applied automatically upon receiving feedback. This process frees up working memory resources, boosting learning efficiency. We test this theory across six experiments. Consistent with our predictions, our findings demonstrate that learning is parametrically impaired by the size of the goal space, but improves when the goal space structure allows for compression. We also find faster reward processing to correlate with better learning performance, supporting the idea that as goal valuation becomes more automatic, more resources are available for learning. We leverage computational modeling to support this interpretation. Our work suggests that efficient goal-directed learning relies on compressing complex goal information into a stable reward function, shedding light on the cognitive mechanisms of human motivation. These findings generate new insights into the neuroscience of intrinsic motivation and could help improve behavioral techniques that support people in achieving their goals.

Related papers

• Aspire: Can Models Self-Evolve from Vague Goals? [61.65007006747275]
  We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution.<n>ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment.<n>Our experiments show that vague goals redirect search effort toward goal interpretation.
  arXiv  Detail & Related papers  (2026-08-31T17:14:59Z)
• Truly Self-Improving Agents Require Intrinsic Metacognitive Learning [59.60803539959191]
  Self-improving agents aim to continuously acquire new capabilities with minimal supervision.<n>Current approaches face two key limitations: their self-improvement processes are often rigid, fail to generalize across tasks domains, and struggle to scale with increasing agent capabilities.<n>We argue that effective self-improvement requires intrinsic metacognitive learning, defined as an agent's intrinsic ability to actively evaluate, reflect on, and adapt its own learning processes.
  arXiv  Detail & Related papers  (2025-06-05T14:53:35Z)
• Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience [89.30876995059168]
  inverse reinforcement learning (IRL) -- inferring the reward function of an agent from observing its behavior. This paper addresses the problem of IRL -- inferring the reward function of an agent from observing its behavior.
  arXiv  Detail & Related papers  (2022-08-09T17:29:49Z)
• Successor Feature Neural Episodic Control [17.706998080391635]
  A longstanding goal in reinforcement learning is to build intelligent agents that show fast learning and a flexible transfer of skills akin to humans and animals. This paper investigates the integration of two frameworks for tackling those goals: episodic control and successor features.
  arXiv  Detail & Related papers  (2021-11-04T19:14:43Z)
• Contrastive Active Inference [12.361539023886161]
  We propose a contrastive objective for active inference that reduces the computational burden in learning the agent's generative model and planning future actions. Our method performs notably better than likelihood-based active inference in image-based tasks, while also being computationally cheaper and easier to train.
  arXiv  Detail & Related papers  (2021-10-19T16:20:49Z)
• Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning [7.6146285961466]
  We extend potential-based reward shaping and propose a subgoal-based reward shaping. Our method makes it easier for human trainers to share their knowledge of subgoals.
  arXiv  Detail & Related papers  (2021-04-13T14:28:48Z)
• Automatic Curriculum Learning through Value Disagreement [95.19299356298876]
  Continually solving new, unsolved tasks is the key to learning diverse behaviors. In the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. We propose setting up an automatic curriculum for goals that the agent needs to solve. We evaluate our method across 13 multi-goal robotic tasks and 5 navigation tasks, and demonstrate performance gains over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-17T03:58:25Z)
• Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning [81.12201426668894]
  We develop efficient reinforcement learning methods that acquire diverse skills without any reward function, and then repurpose these skills for downstream tasks. We show that our proposed algorithm provides substantial improvement in learning efficiency, making reward-free real-world training feasible. We also demonstrate that the learned skills can be composed using model predictive control for goal-oriented navigation, without any additional training.
  arXiv  Detail & Related papers  (2020-04-27T17:38:53Z)
• Intrinsic Motivation for Encouraging Synergistic Behavior [55.10275467562764]
  We study the role of intrinsic motivation as an exploration bias for reinforcement learning in sparse-reward synergistic tasks. Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own.
  arXiv  Detail & Related papers  (2020-02-12T19:34:51Z)
• Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning [102.05692309417047]
  In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals. We propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states.
  arXiv  Detail & Related papers  (2020-02-05T19:21:20Z)

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.