activity
20172022
most citedLearning to Compose Skills

20 citations · 32 across the 4 of their papers we have counts for

collaborators

6 papers

cs.AI2021

Hard Attention Control By Mutual Information Maximization

Himanshu Sahni, Charles Isbell

Biological agents have adopted the principle of attention to limit the rate of incoming information from the environment. One question that arises is if an artificial agent has acc…

cs.LG2020

Estimating Q(s,s') with Deep Deterministic Dynamics Gradients

Ashley D. Edwards, Himanshu Sahni, Rosanne Liu +7

In this paper, we introduce a novel form of value function, , that expresses the utility of transitioning from a state to a neighboring state and then acting opt…

cs.AI2019

Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs

Himanshu Sahni, Toby Buckley, Pieter Abbeel +1

Reinforcement Learning (RL) algorithms typically require millions of environment interactions to learn successful policies in sparse reward settings. Hindsight Experience Replay (H…

cs.LG2018

Imitating Latent Policies from Observation

Ashley D. Edwards, Himanshu Sahni, Yannick Schroecker +1

In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal…

cs.AI201720 cited

Learning to Compose Skills

Himanshu Sahni, Saurabh Kumar, Farhan Tejani +1

We present a differentiable framework capable of learning a wide variety of compositions of simple policies that we call skills. By recursively composing skills with themselves, we…

cs.AI20172 cited

State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning

Himanshu Sahni, Saurabh Kumar, Farhan Tejani +2

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 t…