mlsanityData to 14 Oct 2026

A Bellman Optimality Equation for Plasticity

arXiv 2609.10776 ↗First posted 9 Sep 2026cs.LGcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

In continual reinforcement learning, carefully managing the stability-plasticity tradeoff remains a core challenge. Recent work by Abel et al. (2025) formalized this dilemma by defining plasticity as the generalized directed information from an agent's observations to its actions, and empowerment as the generalized directed information from its actions to its observations. This formulation successfully reframes the traditional stability-plasticity tradeoff as an empowerment-plasticity tradeoff. However, while extensive literature exists on optimizing for empowerment, there is currently no research addressing the optimization of plasticity under this new definition. This paper presents preliminary work toward optimizing plasticity within Markov decision processes. We show that there exists a Bellman optimality equation for optimizing plasticity similar to previous work for empowerment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 9 references that are in the map. First posted on arXiv 9 Sep 2026.

Builds on

6 of 9 references.

References · 6

  1. 2023Understanding plasticity in neural networkscited by 174
  2. 2015Variational Information Maximisation for Intrinsically Motivated Reinforcement Learningcited by 144
  3. 2021Continual Backprop: Stochastic Gradient Descent with Persistent Randomnesscited by 80
  4. 2019A Unified Bellman Optimality Principle Combining Reward Maximization and Empowermentcited by 15
  5. 2025Plasticity as the Mirror of Empowermentcited by 12
  6. 2017A Unified Bellman Equation for Causal Information and Value in Markov Decision Processescited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Activation Function Design Sustains Plasticity in Continual Learning
  2. 2026Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
  3. 2025Information-Theoretic Policy Pre-Training with Empowerment
  4. 2024A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
  5. 2025Rethinking the Foundations for Continual Reinforcement Learning
  6. 2024Plasticity Loss in Deep Reinforcement Learning: A Survey
  7. 2025Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
  8. 2026Balancing Plasticity and Stability with Fast and Slow Successor Features