Prediction and Generative Modeling in Reinforcement Learning

http://reinforcement-learning.ml/pgmrl2018

Sample-Efficient Deep RL with Generative Adversarial Tree Search

Imitating Latent Policies from Observation

Model-based Reinforcement Learning with Non-linear Expectation Models and Stochastic Environments

Hybrid Global Search for Sample Efficient Controller Optimization

Feature Selection by Singular Value Decomposition for Reinforcement Learning

As Expected? An Analysis of Distributional Reinforcement Learning

The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces

Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion

Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning

Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees

Learning and Querying Fast Generative Models for Reinforcement Learning

Navigation and planning in latent maps

Generalizing Value Estimation over Timescale

Failure Modes of Variational Inference for Decision Making

Task-Relevant Embeddings for Robust Perception in Reinforcement Learning

Planning in Dynamic Environments with Conditional Autoregressive Models

VFunc: A Deep Generative Model for Functions

SULFR: Simulation of Urban Logistics for Reinforcement

Iterative Model-Fitting and Local Controller Optimization - Towards a Better Understanding of Convergence Properties

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models