activity
20172022
most citedPlanning to Explore via Self-Supervised World Models

61 citations · 156 across the 12 of their papers we have counts for

collaborators
Showing 2020Show all

5 papers · 1 filter

cs.CV2020

Learning Long-term Visual Dynamics with Region Proposal Interaction Networks

Haozhi Qi, Xiaolong Wang, Deepak Pathak +2

Learning long-term dynamics models is the key to understanding physical common sense. Most existing approaches on learning dynamics from visual input sidestep long-term predictions…

cs.LG202026 cited

One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control

Wenlong Huang, Igor Mordatch, Deepak Pathak

Reinforcement learning is typically concerned with learning control policies tailored to a particular agent. We investigate whether there exists a single global policy that can gen…

cs.LG202061 cited

Planning to Explore via Self-Supervised World Models

Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis +3

Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-…

cs.LG20207 cited

Locally Masked Convolution for Autoregressive Models

Ajay Jain, Pieter Abbeel, Deepak Pathak

High-dimensional generative models have many applications including image compression, multimedia generation, anomaly detection and data completion. State-of-the-art estimators for…

cs.LG2020

Sparse Graphical Memory for Robust Planning

Scott Emmons, Ajay Jain, Michael Laskin +3

To operate effectively in the real world, agents should be able to act from high-dimensional raw sensory input such as images and achieve diverse goals across long time-horizons. C…