Raksha Kumaraswamy
YOU?
Author Swipe
View article: The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning
The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning Open
This paper introduces a new empirical methodology, the Cross-environment Hyperparameter Setting Benchmark, that compares RL algorithms across environments using a single hyperparameter setting, encouraging algorithmic development which is …
View article: Investigating the properties of neural network representations in reinforcement learning
Investigating the properties of neural network representations in reinforcement learning Open
In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis architectures to achieve p…
View article: From eye-blinks to state construction: Diagnostic benchmarks for online representation learning
From eye-blinks to state construction: Diagnostic benchmarks for online representation learning Open
We present three new diagnostic prediction problems inspired by classical-conditioning experiments to facilitate research in online prediction learning. Experiments in classical conditioning show that animals such as rabbits, pigeons, and …
View article: Investigating the Properties of Neural Network Representations in Reinforcement Learning
Investigating the Properties of Neural Network Representations in Reinforcement Learning Open
In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis architectures to achieve p…
View article: Continual Auxiliary Task Learning
Continual Auxiliary Task Learning Open
Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet ther…
View article: Off-Policy Actor-Critic with Emphatic Weightings
Off-Policy Actor-Critic with Emphatic Weightings Open
A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to …
View article: Continual Auxiliary Task Learning
Continual Auxiliary Task Learning Open
Learning auxiliary tasks, such as multiple predictions about the world, can provide many benets to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there …
View article: Prediction problems inspired by animal learning
Prediction problems inspired by animal learning Open
We present three problems modeled after animal learning experiments designed
to test online state construction or representation learning algorithms. Our
test problems require the learning system to construct compact summaries of
their pas…
View article: From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning
From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning Open
We present three new diagnostic prediction problems inspired by classical-conditioning experiments to facilitate research in online prediction learning. Experiments in classical conditioning show that animals such as rabbits, pigeons, and …
View article: Factors influencing mode of delivery in primigravida in rural tertiary care hospital
Factors influencing mode of delivery in primigravida in rural tertiary care hospital Open
Factors influencing mode of delivery in primigravida in rural tertiary care hospital - IJOGR- Print ISSN No: - 2394-2746 Online ISSN No:- 2394-2754 Article DOI No:- 10.18231/j.ijogr.2019.101, Indian Journal of Obstetrics and Gynecology Res…
View article: The Utility of Sparse Representations for Control in Reinforcement Learning
The Utility of Sparse Representations for Control in Reinforcement Learning Open
We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representa…
View article: Context-Dependent Upper-Confidence Bounds for Directed Exploration
Context-Dependent Upper-Confidence Bounds for Directed Exploration Open
Directed exploration strategies for reinforcement learning are critical for learning an optimal policy in a minimal number of interactions with the environment. Many algorithms use optimism to direct exploration, either through visitation …
View article: The Utility of Sparse Representations for Control in Reinforcement Learning
The Utility of Sparse Representations for Control in Reinforcement Learning Open
We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representa…
View article: Learning Sparse Representations in Reinforcement Learning with Sparse Coding
Learning Sparse Representations in Reinforcement Learning with Sparse Coding Open
A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to investigating the utility of sparse coding. Outside of reinforcement learning, sparse coding…
View article: Learning Sparse Representations in Reinforcement Learning with Sparse Coding
Learning Sparse Representations in Reinforcement Learning with Sparse Coding Open
A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to investigating the utility of sparse coding. Outside of reinforcement learning, sparse coding…