arXiv research

Random projection improves stability in neural episodic control.

Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose Neural Episodic Control: a deep reinforcement learning agent that is able to rap…

New algorithm learns reward signals from episodic returns for better reinforcement learning.

Paper proposes DAC-ML, a cognitive architecture that learns quickly from few episodes.

MEMEC improves sample efficiency in reinforcement learning.

Tiny Eats GRU detects eating episodes on a microcontroller.

State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance. Humans, on the other hand, can very quickly exploit highly rewarding nuances of an environment upon first discovery. In the brain, such rapid learning is thought to depend on the hippocampus and…

AE-DDPG improves DDPG for continuous control in complex environments with less data and time.

Logarithmic regret achieved in continuous-time linear-quadratic reinforcement learning.

Single episode policy transfer in RL without access to rewards.

Control of non-episodic, finite-horizon dynamical systems with uncertain dynamics poses a tough and elementary case of the exploration-exploitation trade-off. Bayesian reinforcement learning, reasoning about the effect of actions and future observations, offers a principled solution, but is intractable. We review, then…

Efficiently stores and retrieves past states for faster learning in reinforcement learning.

Study optimal control in unknown nonlinear systems with near-optimal regret bound.

NIPA aims to translate brain learning mechanisms into scalable Bayesian inference.

Bootstrap method for Markov chains in reinforcement learning.

Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.

A new method learns from multi-modal sequences with external memory.

Proposes a new resampling method for off-policy evaluation in stochastic control.

New schemes improve lifelong learning by balancing old and new tasks.

Deep RNN detects FoG episodes in Parkinson's disease with high accuracy.

When applied to training deep neural networks, stochastic gradient descent (SGD) often incurs steady progression phases, interrupted by catastrophic episodes in which loss and gradient norm explode. A possible mitigation of such events is to slow down the learning process. This paper presents a novel approach to contro…

New framework for RL with linear-convex models reduces performance gap.

Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained from psychological studies, we designed a new model called Differentiable Working Memory (DWM) in order to specifically emulate human workin…

Protocol diagnoses neural HJB-PIDE solvers for Lévy jumps, revealing a missing factor in their importance-proposal density.

Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of interaction with the environments to obtain satisfactory performance. Recently,…

We investigate different strategies for active learning with Bayesian deep neural networks. We focus our analysis on scenarios where new, unlabeled data is obtained episodically, such as commonly encountered in mobile robotics applications. An evaluation of different strategies for acquisition, updating, and final trai…

Study of multidimensional control problems with reflection controls.

New Q-learning algorithms reduce regret in inventory control problems.

This paper tackles adaptive control of unknown Markov jump systems with sample complexity and regret bounds.

Proposes PIC and POIC for measuring task difficulty in RL.

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. I…

Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discover…

The success of popular algorithms for deep reinforcement learning, such as policy-gradients and Q-learning, relies heavily on the availability of an informative reward signal at each timestep of the sequential decision-making process. When rewards are only sparsely available during an episode, or a rewarding feedback i…

Paper proposes an intersection decision algorithm for autonomous vehicles.

A novel approach stores encoded images as centroids and covariance matrices to improve classification accuracy with less memory.

New approach uses Gaussian processes to learn and track complex systems with guaranteed accuracy.

New algorithm reduces regret in stochastic shortest path problems.

We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the mode…

New method improves continual learning by anchoring past knowledge.

Proposes a CL technique to improve accuracy and reduce forgetting.

New RL algorithm achieves nearly optimal performance for linear MDPs.

AHA model mimics animal episodic learning without labels.

This work optimizes RL algorithms using entropy regularisation for continuous-time LQ problems.

TapNet uses neural networks with task-adaptive projection for improved few-shot learning.

Deep learning detects microsleep episodes in EEG data.

Meta-learning control algorithm with finite-time guarantees for unknown systems.

Study nonparametric estimator for Markov chain transition matrices in offline setting.

New algorithms for planning with adversarial changes in costs.