pith. sign in

arxiv: 2002.12636 · v1 · pith:R6P5YY7Inew · submitted 2020-02-28 · 💻 cs.LG · cs.AI· cs.IT· cs.SY· eess.SY· math.IT· stat.ML

Reinforcement Learning through Active Inference

classification 💻 cs.LG cs.AIcs.ITcs.SYeess.SYmath.ITstat.ML
keywords activeinferenceagentsexploitationexplorationlearningmaximizereinforcement
0
0 comments X
read the original abstract

The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards. In contrast, active inference, an emerging framework within cognitive and computational neuroscience, proposes that agents act to maximize the evidence for a biased generative model. Here, we illustrate how ideas from active inference can augment traditional RL approaches by (i) furnishing an inherent balance of exploration and exploitation, and (ii) providing a more flexible conceptualization of reward. Inspired by active inference, we develop and implement a novel objective for decision making, which we term the free energy of the expected future. We demonstrate that the resulting algorithm successfully balances exploration and exploitation, simultaneously achieving robust performance on several challenging RL benchmarks with sparse, well-shaped, and no rewards.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Prediction and Empowerment: A Theory of Agency through Bridge Interfaces

    cs.AI 2026-05 unverdicted novelty 7.0

    In deterministic partially observable worlds, perfect prediction requires either identifying the relevant hidden quotient or achieving overwrite control, while high empowerment alone is insufficient.

  2. Multi-Agent Digital Twins for Strategic Decision-Making using Active Inference

    cs.CE 2026-04 unverdicted novelty 6.0

    Multi-agent active inference digital twins with contextual inference and streaming ML integration, illustrated via a Cournot competition socio-economic example.

  3. Exploratory Experience Shapes the Geometry of Predictive Representations

    q-bio.NC 2026-05 unverdicted novelty 5.0

    Exploratory experience produces more spatially organized and transition-preserving predictive representations in maze navigation for both agents and mice.

  4. Active Inference: A method for Phenotyping Agency in AI systems?

    cs.AI 2026-04 unverdicted novelty 4.0

    Active inference offers a variational way to phenotype agency in AI systems by measuring empowerment in generative models via a T-maze paradigm.