Deep learning, reinforcement learning, and world models (2022-04-01T00:00:00.000000Z)

TL;DR

This review of talks and discussions in the "Deep Learning and Reinforcement Learning" session of the symposium, International Symposium on Artificial Intelligence and Brain Science, discusses whether the authors can achieve comprehensive understanding of human intelligence based on the recent advances of deep learning and reinforcement learning algorithms.

Authors

David Silver

21 papers

Yann LeCun

18 papers

Yu Matsuo

1 papers

M. Sahani

1 papers

Doina Precup

4 papers

Masashi Sugiyama

11 papers

E. Uchibe

1 papers

J. Morimoto

1 papers

TL;DR

Authors

References46 items

Reward is enough

The Option Keyboard: Combining Skills in Reinforcement Learning

Composing an Assistive Control Strategy Based on Linear Bellman Combination From Estimated User's Motor Goal

The actions of others act as a pseudo-reward to drive imitation in the context of social reinforcement learning

Forward and inverse reinforcement learning sharing network weights and hyperparameters

Fast reinforcement learning with generalized policy updates

Meta-Gradient Reinforcement Learning with an Objective Discovered Online

A Neuro-computational Account of Arbitration between Choice Imitation and Goal Emulation during Human Observational Learning

Full-Body Optimal Control Toward Versatile and Agile Behaviors in a Humanoid Robot

Hierarchical motor control in mammals and machines

Mastering Atari, Go, chess and shogi by planning with a learned model

Deep reinforcement learning with smooth policy update: Application to robotic cloth manipulation

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Human-In-The-Loop Control and Task Learning for Pneumatically Actuated Muscle Based Robots

Towards learning-to-learn

Neural probabilistic motor primitives for humanoid control

Multi-task Deep Reinforcement Learning with PopArt

Model-Free Deep Inverse Reinforcement Learning by Logistic Regression

An Algorithmic Perspective on Imitation Learning

Neural computations underlying inverse reinforcement learning in the human brain

Mastering the game of Go without human knowledge

Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving

The hippocampus as a predictive map

The successor representation in human reinforcement learning

Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection

Trial and Error: Using Previous Experiences as Simulation Models in Humanoid Motor Learning

Mastering the game of Go with deep neural networks and tree search

Dynamic Linear Bellman Combination of Optimal Policies for Solving New Tasks

Probabilistic machine learning and artificial intelligence

Human-level control through deep reinforcement learning

Efficient Sample Reuse in Policy Gradients with Parameter-Based Exploration

Darwinian embodied evolution of the learning ability for survival

Compositionality of optimal control laws

Nonparametric representation of an approximated Poincaré map for learning biped locomotion

Linear Bellman combination for control of character animation

Efficient computation of optimal actions

Extracting and composing robust features with denoising autoencoders

Doubly Distributional Population Codes: Simultaneous Representation of Uncertainty and Multiplicity

Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning

Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning

Is imitation learning the route to humanoid robots?

Improving Generalization for Temporal Difference Learning: The Successor Representation

Feudal Reinforcement Learning

A Canonical Microcircuit for Neocortex

To appear in : Neural Computation , 10 ( 2 ) , 403-430 Probabilistic Interpretation of Population Codes

Distributed hierarchical processing in the primate cerebral cortex.

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names