This paper introduces a local search method for improving an existing pr...
Tomorrow's robots will need to distinguish useful information from noise...
Driving SMARTS is a regular competition designed to tackle problems caus...
We propose an AI-based pilot trainer to help students learn how to fly
a...
We propose Reinforcement Teaching: a framework for meta-learning in whic...
Reinforcement learning (RL) has shown great success in solving many
chal...
Learning to collaborate is critical in Multi-Agent Reinforcement Learnin...
Learning representations for pixel-based control has garnered significan...
Reinforcement learning has made great strides in recent years due to the...
Some reinforcement learning methods suffer from high sample complexity
c...
Accuracy and generalization of dynamics models is key to the success of
...
Reinforcement learning (RL) is a popular machine learning paradigm for g...
Cooperative multi-agent reinforcement learning (MARL) has achieved
signi...
Reinforcement learning is a powerful learning paradigm in which agents c...
Reinforcement learning (RL) algorithms typically deal with maximizing th...
Experience replay (ER) improves the data efficiency of off-policy
reinfo...
A long-term goal of reinforcement learning agents is to be able to perfo...
Predictive auxiliary tasks have been shown to improve performance in num...
Reinforcement learning (RL) is a popular paradigm for addressing sequent...
Mean field theory provides an effective way of scaling multiagent
reinfo...
How to best explore in domains with sparse, delayed, and deceptive rewar...
Deep reinforcement learning has achieved great successes in recent years...
Deep reinforcement learning has achieved great successes in recent years...
In this paper we explore how actor-critic methods in deep reinforcement
...
In order for robots and other artificial agents to efficiently learn to
...
The Pommerman Team Environment is a recently proposed benchmark which
in...
Safe reinforcement learning has many variants and it is still an open
re...
Deep Reinforcement Learning (DRL) algorithms are known to be data
ineffi...
Deep reinforcement learning (deep RL) has achieved superior performance ...
Deep reinforcement learning (DRL) has achieved great successes in recent...
Reinforcement learning (RL) techniques, while often powerful, can suffer...
Deep reinforcement learning (DRL) has achieved outstanding results in re...
Reinforcement Learning (RL) can be extremely effective in solving comple...
Reinforcement learning has enjoyed multiple successes in recent years.
H...
Reinforcement learning (RL) has had many successes in both "deep" and
"s...
Reinforcement learning (RL), while often powerful, can suffer from slow
...
Deep reinforcement learning (deep RL) has achieved superior performance ...
In this article we study the transfer learning model of action advice un...
For agents and robots to become more useful, they must be able to quickl...