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 …
formalization of intelligent decision making that is powerful and broadly applicable. While …
Planning in the brain
Recent breakthroughs in artificial intelligence (AI) have enabled machines to plan in tasks
previously thought to be uniquely human. Meanwhile, the planning algorithms implemented …
previously thought to be uniquely human. Meanwhile, the planning algorithms implemented …
Gflownet foundations
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 …
diverse set of candidates in an active learning context, with a training objective that makes …
A distributional perspective on reinforcement learning
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 …
distribution of the random return received by a reinforcement learning agent. This is in …
A survey of inverse reinforcement learning
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 …
environment from examples provided by a teacher. Inverse reinforcement learning (IRL) is a …
Efficient exploration via state marginal matching
Exploration is critical to a reinforcement learning agent's performance in its given
environment. Prior exploration methods are often based on using heuristic auxiliary …
environment. Prior exploration methods are often based on using heuristic auxiliary …
Sentience and the origins of consciousness: From Cartesian duality to Markovian monism
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 …
physics and information theory. Our agenda is to describe a key distinction in the physical …
Active inference and epistemic value
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 …
the expected free energy of future outcomes. Crucially, the negative free energy or quality of …
Internal models in biological control
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 …
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
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 …
derived automatically from a model of the actions, sensors, and goals. The main challenges …