activity
20172021
most citedOpen-Ended Learning Leads to Generally Capable Agents

55 citations · 151 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG202155 cited

Open-Ended Learning Leads to Generally Capable Agents

Open Ended Learning Team, Adam Stooke, Anuj Mahajan +15

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We…

math.OC202044 cited

Responsive Safety in Reinforcement Learning by PID Lagrangian Methods

Adam Stooke, Joshua Achiam, Pieter Abbeel

Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe rein…

cs.AI20201 cited

Perception-Prediction-Reaction Agents for Deep Reinforcement Learning

Adam Stooke, Valentin Dalibard, Siddhant M. Jayakumar +2

We introduce a new recurrent agent architecture and associated auxiliary losses which improve reinforcement learning in partially observable tasks requiring long-term memory. We em…

cs.LG2020

Reinforcement Learning with Augmented Data

Michael Laskin, Kimin Lee, Adam Stooke +3

Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks…

cs.LG201951 cited

rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch

Adam Stooke, Pieter Abbeel

Since the recent advent of deep reinforcement learning for game play and simulated robotic control, a multitude of new algorithms have flourished. Most are model-free algorithms wh…

cs.LG2018

Accelerated Methods for Deep Reinforcement Learning

Adam Stooke, Pieter Abbeel

Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice. We investigate how to opt…