[HTML][HTML] The free energy principle made simpler but not too simple
This paper provides a concise description of the free energy principle, starting from a
formulation of random dynamical systems in terms of a Langevin equation and ending with a …
formulation of random dynamical systems in terms of a Langevin equation and ending with a …
Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges
Continual learning (CL) is a particular machine learning paradigm where the data
distribution and learning objective change through time, or where all the training data and …
distribution and learning objective change through time, or where all the training data and …
Is pessimism provably efficient for offline rl?
We study offline reinforcement learning (RL), which aims to learn an optimal policy based on
a dataset collected a priori. Due to the lack of further interactions with the environment …
a dataset collected a priori. Due to the lack of further interactions with the environment …
Planning to explore via self-supervised world models
Reinforcement learning allows solving complex tasks, however, the learning tends to be task-
specific and the sample efficiency remains a challenge. We present Plan2Explore, a self …
specific and the sample efficiency remains a challenge. We present Plan2Explore, a self …
An introduction to deep reinforcement learning
Deep reinforcement learning is the combination of reinforcement learning (RL) and deep
learning. This field of research has been able to solve a wide range of complex …
learning. This field of research has been able to solve a wide range of complex …
Graph networks as learnable physics engines for inference and control
A Sanchez-Gonzalez, N Heess… - International …, 2018 - proceedings.mlr.press
Understanding and interacting with everyday physical scenes requires rich knowledge
about the structure of the world, represented either implicitly in a value or policy function, or …
about the structure of the world, represented either implicitly in a value or policy function, or …
Curiosity-driven exploration by self-supervised prediction
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent
altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the …
altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the …
Self-supervised exploration via disagreement
Efficient exploration is a long-standing problem in sensorimotor learning. Major advances
have been demonstrated in noise-free, non-stochastic domains such as video games and …
have been demonstrated in noise-free, non-stochastic domains such as video games and …
Discovering and achieving goals via world models
How can artificial agents learn to solve many diverse tasks in complex visual environments
without any supervision? We decompose this question into two challenges: discovering new …
without any supervision? We decompose this question into two challenges: discovering new …
# exploration: A study of count-based exploration for deep reinforcement learning
Count-based exploration algorithms are known to perform near-optimally when used in
conjunction with tabular reinforcement learning (RL) methods for solving small discrete …
conjunction with tabular reinforcement learning (RL) methods for solving small discrete …