44 citations · 56 across the 14 of their papers we have counts for
15 papers
Offline RLAIF: Piloting VLM Feedback for RL via SFO
Jacob Beck
While internet-scale image and textual data have enabled strong generalization in Vision-Language Models (VLMs), the absence of internet-scale control data has impeded the developm…
A Survey of In-Context Reinforcement Learning
Amir Moeini, Jiuqi Wang, Jacob Beck +4
Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new…
Metalic: Meta-Learning In-Context with Protein Language Models
Jacob Beck, Shikha Surana, Manus McAuliffe +4
Predicting the biophysical and functional properties of proteins is essential for in silico protein design. Machine learning has emerged as a promising technique for such predictio…
SplAgger: Split Aggregation for Meta-Reinforcement Learning
Jacob Beck, Matthew Jackson, Risto Vuorio +2
A core ambition of reinforcement learning (RL) is the creation of agents capable of rapid learning in novel tasks. Meta-RL aims to achieve this by directly learning such agents. Bl…
Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
Zheng Xiong, Risto Vuorio, Jacob Beck +3
Learning a universal policy across different robot morphologies can significantly improve learning efficiency and enable zero-shot generalization to unseen morphologies. However, l…
Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
Jacob Beck, Risto Vuorio, Zheng Xiong +1
Deep reinforcement learning (RL) is notoriously impractical to deploy due to sample inefficiency. Meta-RL directly addresses this sample inefficiency by learning to perform few-sho…
Universal Morphology Control via Contextual Modulation
Zheng Xiong, Jacob Beck, Shimon Whiteson
Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. However, it poses a challeng…
A Tutorial on Meta-Reinforcement Learning
Jacob Beck, Risto Vuorio, Evan Zheran Liu +4
While deep reinforcement learning (RL) has fueled multiple high-profile successes in machine learning, it is held back from more widespread adoption by its often poor data efficien…
Hypernetworks in Meta-Reinforcement Learning
Jacob Beck, Matthew Thomas Jackson, Risto Vuorio +1
Training a reinforcement learning (RL) agent on a real-world robotics task remains generally impractical due to sample inefficiency. Multi-task RL and meta-RL aim to improve sample…
An Investigation of the Bias-Variance Tradeoff in Meta-Gradients
Risto Vuorio, Jacob Beck, Shimon Whiteson +2
Meta-gradients provide a general approach for optimizing the meta-parameters of reinforcement learning (RL) algorithms. Estimation of meta-gradients is central to the performance o…
Trust Region Bounds for Decentralized PPO Under Non-stationarity
Mingfei Sun, Sam Devlin, Jacob Beck +2
We present trust region bounds for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL), which holds even when the transition dynamics are non…
On the Practical Consistency of Meta-Reinforcement Learning Algorithms
Zheng Xiong, Luisa Zintgraf, Jacob Beck +2
Consistency is the theoretical property of a meta learning algorithm that ensures that, under certain assumptions, it can adapt to any task at test time. An open question is whethe…
Stackelberg Punishment and Bully-Proofing Autonomous Vehicles
Matt Cooper, Jun Ki Lee, Jacob Beck +7
Mutually beneficial behavior in repeated games can be enforced via the threat of punishment, as enshrined in game theory's well-known "folk theorem." There is a cost, however, to a…
ReNeg and Backseat Driver: Learning from Demonstration with Continuous Human Feedback
Jacob Beck, Zoe Papakipos, Michael Littman
In autonomous vehicle (AV) control, allowing mistakes can be quite dangerous and costly in the real world. For this reason we investigate methods of training an AV without allowing…
Neural Mesh: Introducing a Notion of Space and Conservation of Energy to Neural Networks
Jacob Beck, Zoe Papakipos
Neural networks are based on a simplified model of the brain. In this project, we wanted to relax the simplifying assumptions of a traditional neural network by making a model that…