This paper improves robot grasping by integrating meta-control and latent-space imagination.
problem Dual-system approaches fail to consider the reliability of the learned model when making multiple-step predictions.
method A meta-controller arbitrates between model-based and model-free decisions based on local reliability, encouraging actions that improve the model and generating imagined experiences for additional training.
result Our approach learns near-optimal grasping policies in dense- and sparse-reward environments, outperforming baseline and state-of-the-art methods.
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, s…
Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world dynamics and model errors inevitable in complex domains. However, they require a lo…
We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, w…
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transformation operations that…
RG-TTA adapts neural forecasters to streaming time series shifts by modulating adaptation intensity.
problem Adapting neural forecasters to distribution shifts in streaming time series data.
method RG-TTA uses a meta-controller that continuously modulates adaptation intensity based on distributional similarity.
result RG-TTA achieves the lowest MSE in 156 of 224 seed-averaged experiments, reducing MSE by 5.7% vs TTA.
A core aspect of human intelligence is the ability to learn new tasks quickly and switch between them flexibly. Here, we describe a modular continual reinforcement learning paradigm inspired by these abilities. We first introduce a visual interaction environment that allows many types of tasks to be unified in a single…
In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity saturation because a neural network's ability to generalize to new concepts is limite…
Male infertility is a disease which affects approximately 7% of men. Sperm morphology analysis (SMA) is one of the main diagnosis methods for this problem. Manual SMA is an inexact, subjective, non-reproducible, and hard to teach process. As a result, in this paper, we introduce a novel automatic SMA based on a neural …