Exploration strategies in continuous action space are often heuristic du...
Baird counterexample was proposed by Leemon Baird in 1995, first used to...
Gradient Temporal Difference (GTD) algorithms (Sutton et al., 2008, 2009...
We show that unlike machine learning classifiers, there are no complex
b...
Recognizing and telling similar objects apart is even hard for human bei...
One of the major difficulties of reinforcement learning is learning from...
Gradient descent is slow to converge for ill-conditioned problems and
no...
Autonomous driving has achieved a significant milestone in research and
...
There has been growing interest in the development and deployment of
aut...
In real scenarios, state observations that an agent observes may contain...
The deadly triad refers to the instability of a reinforcement learning
a...
Off-policy policy optimization is a challenging problem in reinforcement...
Model-based reinforcement learning (MBRL) can significantly improve samp...
Catastrophic interference is common in many network-based learning syste...
Significant progress has been made recently in developing few-shot objec...
Conventional few-shot object segmentation methods learn object segmentat...
We present the first provably convergent off-policy actor-critic algorit...
We propose a method to tackle the problem of mapless collision-avoidance...
Gradient-based meta-learning has proven to be highly effective at learni...
Dyna is an architecture for model-based reinforcement learning (RL), whe...
In distributional reinforcement learning (RL), the estimated distributio...
Adversary scenarios in driving, where the other vehicles may make mistak...
Learning an effective representation for high-dimensional data is a
chal...
In this paper, we propose an actor ensemble algorithm, named ACE, for
co...
In this paper, we propose the Quantile Option Architecture (QUOTA) for
e...
In deep neural network, the cross-entropy loss function is commonly used...
The problem of action-conditioned image prediction is to predict the exp...