What matters in on-policy reinforcement learning? a large-scale empirical study
In recent years, on-policy reinforcement learning (RL) has been successfully applied to
many different continuous control tasks. While RL algorithms are often conceptually simple …
many different continuous control tasks. While RL algorithms are often conceptually simple …
What matters for on-policy deep actor-critic methods? a large-scale study
In recent years, reinforcement learning (RL) has been successfully applied to many different
continuous control tasks. While RL algorithms are often conceptually simple, their state-of …
continuous control tasks. While RL algorithms are often conceptually simple, their state-of …
Evolving rewards to automate reinforcement learning
Many continuous control tasks have easily formulated objectives, yet using them directly as
a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many …
a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many …
Awac: Accelerating online reinforcement learning with offline datasets
Reinforcement learning (RL) provides an appealing formalism for learning control policies
from experience. However, the classic active formulation of RL necessitates a lengthy active …
from experience. However, the classic active formulation of RL necessitates a lengthy active …
P3o: Policy-on policy-off policy optimization
R Fakoor, P Chaudhari… - Uncertainty in artificial …, 2020 - proceedings.mlr.press
On-policy reinforcement learning (RL) algorithms have high sample complexity while off-
policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient …
policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient …
Keep doing what worked: Behavioral modelling priors for offline reinforcement learning
NY Siegel, JT Springenberg, F Berkenkamp… - arXiv preprint arXiv …, 2020 - arxiv.org
Off-policy reinforcement learning algorithms promise to be applicable in settings where only
a fixed data-set (batch) of environment interactions is available and no new experience can …
a fixed data-set (batch) of environment interactions is available and no new experience can …
Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is
beginning to show some successes in real-world scenarios. However, much of the research …
beginning to show some successes in real-world scenarios. However, much of the research …
Advantage-weighted regression: Simple and scalable off-policy reinforcement learning
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that
uses standard supervised learning methods as subroutines. Our goal is an algorithm that …
uses standard supervised learning methods as subroutines. Our goal is an algorithm that …
The in-sample softmax for offline reinforcement learning
Reinforcement learning (RL) agents can leverage batches of previously collected data to
extract a reasonable control policy. An emerging issue in this offline RL setting, however, is …
extract a reasonable control policy. An emerging issue in this offline RL setting, however, is …
An empirical investigation of the challenges of real-world reinforcement learning
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is
beginning to show some successes in real-world scenarios. However, much of the research …
beginning to show some successes in real-world scenarios. However, much of the research …