Learning Policy Representations for Steerable Behavior Synthesis

• URL: http://arxiv.org/abs/2601.22350v1
• Date: Thu, 29 Jan 2026 21:52:06 GMT
• Title: Learning Policy Representations for Steerable Behavior Synthesis
• Authors: Beiming Li, Sergio Rozada, Alejandro Ribeiro,
• Abstract summary: Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time.<n>We show that these representations can be approximated uniformly for a range of policies using a set-based architecture.<n>We use variational generative approach to induce a smooth latent space, and further shape it with contrastive learning so that latent distances align with differences in value functions.
• Score: 80.4542176039074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time. As policies of an MDP are uniquely determined by their occupancy measures, we propose modeling policy representations as expectations of state-action feature maps with respect to occupancy measures. We show that these representations can be approximated uniformly for a range of policies using a set-based architecture. Our model encodes a set of state-action samples into a latent embedding, from which we decode both the policy and its value functions corresponding to multiple rewards. We use variational generative approach to induce a smooth latent space, and further shape it with contrastive learning so that latent distances align with differences in value functions. This geometry permits gradient-based optimization directly in the latent space. Leveraging this capability, we solve a novel behavior synthesis task, where policies are steered to satisfy previously unseen value function constraints without additional training.

Related papers

• Policy-Conditioned Policies for Multi-Agent Task Solving [53.67744322553693]
  In this work, we propose a paradigm shift that bridges the gap by representing policies as human-interpretable source code.<n>We reformulate the learning problem by utilizing Large Language Models (LLMs) as approximate interpreters.<n>We formalize this process as textitProgrammatic Iterated Best Response (PIBR), an algorithm where the policy code is optimized by textual gradients.
  arXiv  Detail & Related papers  (2025-12-24T07:42:10Z)
• Proto Successor Measure: Representing the Behavior Space of an RL Agent [37.55496993803242]
  "Zero-shot learning" is elusive for general-purpose reinforcement learning algorithms.<n>We present Proto Successor Measure: the basis set for all possible behaviors of a Reinforcement Learning Agent.<n>We derive a practical algorithm to learn these basis functions using reward-free interaction data from the environment.
  arXiv  Detail & Related papers  (2024-11-29T00:09:39Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability [2.180257135067774]
  We introduce a policy-gradient method for model-based reinforcement learning (RL)<n>We exploit a type of stationary distributions commonly obtained from Markov decision processes (MDPs) in networks.<n>We show that SAGE-based policy-gradient locally converges, and we obtain its regret.
  arXiv  Detail & Related papers  (2023-12-05T14:44:58Z)
• Policy Gradient Methods in the Presence of Symmetries and State Abstractions [46.66541516203923]
  Reinforcement learning (RL) on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization. We study abstraction in the continuous-control setting, and extend the definition of Markov decision process (MDP) homomorphisms to the setting of continuous state and action spaces. We propose a family of actor-critic algorithms that are able to learn the policy and the MDP homomorphism map simultaneously.
  arXiv  Detail & Related papers  (2023-05-09T17:59:10Z)
• Goal-Conditioned Imitation Learning using Score-based Diffusion Policies [3.49482137286472]
  We propose a new policy representation based on score-based diffusion models (SDMs) We apply our new policy representation in the domain of Goal-Conditioned Imitation Learning (GCIL) We show how BESO can even be used to learn a goal-independent policy from play-data usingintuitive-free guidance.
  arXiv  Detail & Related papers  (2023-04-05T15:52:34Z)
• Policy Dispersion in Non-Markovian Environment [53.05904889617441]
  This paper tries to learn the diverse policies from the history of state-action pairs under a non-Markovian environment. We first adopt a transformer-based method to learn policy embeddings. Then, we stack the policy embeddings to construct a dispersion matrix to induce a set of diverse policies.
  arXiv  Detail & Related papers  (2023-02-28T11:58:39Z)
• Continuous MDP Homomorphisms and Homomorphic Policy Gradient [51.25171126424949]
  We extend the definition of MDP homomorphisms to encompass continuous actions in continuous state spaces. We propose an actor-critic algorithm that is able to learn the policy and the MDP homomorphism map simultaneously.
  arXiv  Detail & Related papers  (2022-09-15T15:26:49Z)
• Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms [1.776746672434207]
  We study policy gradient (PG) for reinforcement learning in continuous time and space. We propose two types of the actor-critic algorithms for RL, where we learn and update value functions and policies simultaneously and alternatingly.
  arXiv  Detail & Related papers  (2021-11-22T14:27:04Z)
• Towards Robust Bisimulation Metric Learning [3.42658286826597]
  Bisimulation metrics offer one solution to representation learning problem. We generalize value function approximation bounds for on-policy bisimulation metrics to non-optimal policies. We find that these issues stem from an underconstrained dynamics model and an unstable dependence of the embedding norm on the reward signal.
  arXiv  Detail & Related papers  (2021-10-27T00:32:07Z)
• Composable Learning with Sparse Kernel Representations [110.19179439773578]
  We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space. We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function. We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner while navigating in a 2D environment.
  arXiv  Detail & Related papers  (2021-03-26T13:58:23Z)

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.