Daniel J. Mankowitz

is this you? claim profile

Research Scientist at DeepMind. Doctor of Philosophy (Ph.D.) Reinforcement Learning at Technion Israel Institute of Technology.

Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification

Many real-world physical control systems are required to satisfy constra...
10/20/2020 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Balancing Constraints and Rewards with Meta-Gradient D4PG

Deploying Reinforcement Learning (RL) agents to solve real-world applica...
10/13/2020 ∙ by Dan A. Calian, et al. ∙ 0 ∙ share

read it
An empirical investigation of the challenges of real-world reinforcement learning

Reinforcement learning (RL) has proven its worth in a series of artifici...
03/24/2020 ∙ by Gabriel Dulac-Arnold, et al. ∙ 9 ∙ share

read it
Robust Reinforcement Learning for Continuous Control with Model Misspecification

We provide a framework for incorporating robustness -- to perturbations ...
06/18/2019 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces

We propose a computationally efficient algorithm that combines compresse...
05/23/2019 ∙ by Chen Tessler, et al. ∙ 0 ∙ share

read it
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Learning how to act when there are many available actions in each state ...
09/06/2018 ∙ by Tom Zahavy, et al. ∙ 6 ∙ share

read it
Reward Constrained Policy Optimization

Teaching agents to perform tasks using Reinforcement Learning is no easy...
05/28/2018 ∙ by Chen Tessler, et al. ∙ 0 ∙ share

read it
Soft-Robust Actor-Critic Policy-Gradient

Robust Reinforcement Learning aims to derive an optimal behavior that ac...
03/11/2018 ∙ by Esther Derman, et al. ∙ 0 ∙ share

read it
Unicorn: Continual Learning with a Universal, Off-policy Agent

Some real-world domains are best characterized as a single task, but for...
02/22/2018 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Learning Robust Options

Robust reinforcement learning aims to produce policies that have strong ...
02/09/2018 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Situationally Aware Options

Hierarchical abstractions, also known as options -- a type of temporally...
11/20/2017 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Shallow Updates for Deep Reinforcement Learning

Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQ...
05/21/2017 ∙ by Nir Levine, et al. ∙ 0 ∙ share

read it
Situational Awareness by Risk-Conscious Skills

Hierarchical Reinforcement Learning has been previously shown to speed u...
10/10/2016 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Adaptive Skills, Adaptive Partitions (ASAP)

We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework t...
02/10/2016 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Iterative Hierarchical Optimization for Misspecified Problems (IHOMP)

For complex, high-dimensional Markov Decision Processes (MDPs), it may b...
02/10/2016 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
CFORB: Circular FREAK-ORB Visual Odometry

We present a novel Visual Odometry algorithm entitled Circular FREAK-ORB...
06/17/2015 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Bootstrapping Skills

The monolithic approach to policy representation in Markov Decision Proc...
06/11/2015 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it

Daniel J. Mankowitz

Featured Co-authors

Shie Mannor

Doina Precup

Nicolas Heess

David Silver

Aviv Tamar

Jerry Li

Martin Riedmiller

Hado van Hasselt

Jost Tobias Springenberg

Tom Schaul

Tom Zahavy

Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification

Balancing Constraints and Rewards with Meta-Gradient D4PG

An empirical investigation of the challenges of real-world reinforcement learning

Robust Reinforcement Learning for Continuous Control with Model Misspecification

Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Reward Constrained Policy Optimization

Soft-Robust Actor-Critic Policy-Gradient

Unicorn: Continual Learning with a Universal, Off-policy Agent

Learning Robust Options

Situationally Aware Options

Shallow Updates for Deep Reinforcement Learning

Situational Awareness by Risk-Conscious Skills

Adaptive Skills, Adaptive Partitions (ASAP)

Iterative Hierarchical Optimization for Misspecified Problems (IHOMP)

CFORB: Circular FREAK-ORB Visual Odometry

Bootstrapping Skills