Reinforcement learning and control as probabilistic inference: Tutorial and review

S Levine - arxiv preprint arxiv:1805.00909, 2018 - arxiv.org
The framework of reinforcement learning or optimal control provides a mathematical
formalization of intelligent decision making that is powerful and broadly applicable. While …

Planning in the brain

MG Mattar, M Lengyel - Neuron, 2022 - cell.com
Recent breakthroughs in artificial intelligence (AI) have enabled machines to plan in tasks
previously thought to be uniquely human. Meanwhile, the planning algorithms implemented …

Gflownet foundations

Y Bengio, S Lahlou, T Deleu, EJ Hu, M Tiwari… - The Journal of Machine …, 2023 - dl.acm.org
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a
diverse set of candidates in an active learning context, with a training objective that makes …

A distributional perspective on reinforcement learning

MG Bellemare, W Dabney… - … conference on machine …, 2017 - proceedings.mlr.press
In this paper we argue for the fundamental importance of the value distribution: the
distribution of the random return received by a reinforcement learning agent. This is in …

A survey of inverse reinforcement learning

S Adams, T Cody, PA Beling - Artificial Intelligence Review, 2022 - Springer
Learning from demonstration, or imitation learning, is the process of learning to act in an
environment from examples provided by a teacher. Inverse reinforcement learning (IRL) is a …

Efficient exploration via state marginal matching

L Lee, B Eysenbach, E Parisotto, E **ng… - arxiv preprint arxiv …, 2019 - arxiv.org
Exploration is critical to a reinforcement learning agent's performance in its given
environment. Prior exploration methods are often based on using heuristic auxiliary …

Sentience and the origins of consciousness: From Cartesian duality to Markovian monism

KJ Friston, W Wiese, JA Hobson - Entropy, 2020 - mdpi.com
This essay addresses Cartesian duality and how its implicit dialectic might be repaired using
physics and information theory. Our agenda is to describe a key distinction in the physical …

Active inference and epistemic value

K Friston, F Rigoli, D Ognibene, C Mathys… - Cognitive …, 2015 - Taylor & Francis
We offer a formal treatment of choice behavior based on the premise that agents minimize
the expected free energy of future outcomes. Crucially, the negative free energy or quality of …

Internal models in biological control

D McNamee, DM Wolpert - Annual review of control, robotics …, 2019 - annualreviews.org
Rationality principles such as optimal feedback control and Bayesian inference underpin a
probabilistic framework that has accounted for a range of empirical phenomena in biological …

[LIBRO][B] A concise introduction to models and methods for automated planning

H Geffner, B Bonet - 2013 - books.google.com
Planning is the model-based approach to autonomous behavior where the agent behavior is
derived automatically from a model of the actions, sensors, and goals. The main challenges …