Active Inference in Robotics and Artificial Agents: Survey and
Challenges
- URL: http://arxiv.org/abs/2112.01871v1
- Date: Fri, 3 Dec 2021 12:10:26 GMT
- Title: Active Inference in Robotics and Artificial Agents: Survey and
Challenges
- Authors: Pablo Lanillos, Cristian Meo, Corrado Pezzato, Ajith Anil Meera,
Mohamed Baioumy, Wataru Ohata, Alexander Tschantz, Beren Millidge, Martijn
Wisse, Christopher L. Buckley, Jun Tani
- Abstract summary: We review the state-of-the-art theory and implementations of active inference for state-estimation, control, planning and learning.
We showcase relevant experiments that illustrate its potential in terms of adaptation, generalization and robustness.
- Score: 51.29077770446286
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Active inference is a mathematical framework which originated in
computational neuroscience as a theory of how the brain implements action,
perception and learning. Recently, it has been shown to be a promising approach
to the problems of state-estimation and control under uncertainty, as well as a
foundation for the construction of goal-driven behaviours in robotics and
artificial agents in general. Here, we review the state-of-the-art theory and
implementations of active inference for state-estimation, control, planning and
learning; describing current achievements with a particular focus on robotics.
We showcase relevant experiments that illustrate its potential in terms of
adaptation, generalization and robustness. Furthermore, we connect this
approach with other frameworks and discuss its expected benefits and
challenges: a unified framework with functional biological plausibility using
variational Bayesian inference.
Related papers
- Active Inference Meeting Energy-Efficient Control of Parallel and Identical Machines [1.693200946453174]
We investigate the application of active inference in developing energy-efficient control agents for manufacturing systems.
Our study explores deep active inference, an emerging field that combines deep learning with the active inference decision-making framework.
arXiv Detail & Related papers (2024-06-13T17:00:30Z) - Dynamic planning in hierarchical active inference [0.0]
We refer to the ability of the human brain to infer and impose motor trajectories related to cognitive decisions.
This study distances from traditional views centered on neural networks and reinforcement learning, and points toward a yet unexplored direction in active inference.
arXiv Detail & Related papers (2024-02-18T17:32:53Z) - Active Inference as a Model of Agency [1.9019250262578857]
We show that any behaviour complying with physically sound assumptions about how biological agents interact with the world integrates exploration and exploitation.
This description, known as active inference, refines the free energy principle, a popular descriptive framework for action and perception originating in neuroscience.
arXiv Detail & Related papers (2024-01-23T17:09:25Z) - Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [55.65482030032804]
Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning.
We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures.
Our approach infers dynamically evolving relation graphs and hypergraphs to capture the evolution of relations, which the trajectory predictor employs to generate future states.
arXiv Detail & Related papers (2024-01-22T18:58:22Z) - Towards a General Framework for Continual Learning with Pre-training [55.88910947643436]
We present a general framework for continual learning of sequentially arrived tasks with the use of pre-training.
We decompose its objective into three hierarchical components, including within-task prediction, task-identity inference, and task-adaptive prediction.
We propose an innovative approach to explicitly optimize these components with parameter-efficient fine-tuning (PEFT) techniques and representation statistics.
arXiv Detail & Related papers (2023-10-21T02:03:38Z) - Bayesian Reinforcement Learning with Limited Cognitive Load [43.19983737333797]
Theory of adaptive behavior should account for complex interactions between an agent's learning history, decisions, and capacity constraints.
Recent work in computer science has begun to clarify the principles that shape these dynamics by bridging ideas from reinforcement learning, Bayesian decision-making, and rate-distortion theory.
arXiv Detail & Related papers (2023-05-05T03:29:34Z) - Interpreting Neural Policies with Disentangled Tree Representations [58.769048492254555]
We study interpretability of compact neural policies through the lens of disentangled representation.
We leverage decision trees to obtain factors of variation for disentanglement in robot learning.
We introduce interpretability metrics that measure disentanglement of learned neural dynamics.
arXiv Detail & Related papers (2022-10-13T01:10:41Z) - The Free Energy Principle for Perception and Action: A Deep Learning
Perspective [4.6956495676681484]
The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world.
Under this principle, biological agents learn a generative model of the world and plan actions in the future that will maintain the agent in a homeostatic state that satisfies its preferences.
This manuscript probes newer perspectives for the active inference framework, grounding its theoretical aspects into more pragmatic affairs.
arXiv Detail & Related papers (2022-07-13T11:07:03Z) - Behavior Priors for Efficient Reinforcement Learning [97.81587970962232]
We consider how information and architectural constraints can be combined with ideas from the probabilistic modeling literature to learn behavior priors.
We discuss how such latent variable formulations connect to related work on hierarchical reinforcement learning (HRL) and mutual information and curiosity based objectives.
We demonstrate the effectiveness of our framework by applying it to a range of simulated continuous control domains.
arXiv Detail & Related papers (2020-10-27T13:17:18Z) - Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches.
Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
arXiv Detail & Related papers (2020-03-09T15:04:07Z)
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.