AIConfPaper
← Search

Angelos Filos

10 accepted papers

2024

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

Andrew Jesson, Chris Lu, Gunshi Gupta, Nicolas Beltran-Velez, Angelos Filos, Jakob Nicolaus Foerster +1
ICML 2024poster

This paper proposes a step toward approximate Bayesian inference in on-policy actor-critic deep reinforcement learning. It is implemented through three changes to the Asynchronous Advantage Actor-Critic (A3C) algorithm: (1) applying a ReLU function to advantage estimates, (2) spectral normalization…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2023

Combining Behaviors with the Successor Features Keyboard

Wilka Carvalho, Andre Saraiva, Angelos Filos, Andrew Kyle Lampinen, Loic Matthey, Richard Lewis +4
NeurIPS 2023poster

The Option Keyboard (OK) was recently proposed as a method for transferring behavioral knowledge across tasks. OK transfers knowledge by adaptively combining subsets of known behaviors using Successor Features (SFs) and Generalized Policy Improvement (GPI). However, it relies on hand-designed state-…

Cited by 7Source ↗PDF ↗Scholar ↗
2023

Composing Task Knowledge With Modular Successor Feature Approximators

Wilka Torrico Carvalho, Angelos Filos, Richard Lewis, Honglak Lee, Satinder Singh
ICLR 2023poster

Recently, the Successor Features and Generalized Policy Improvement (SF&GPI) framework has been proposed as a method for learning, composing and transferring predictive knowledge and behavior. SF&GPI works by having an agent learn predictive representations (SFs) that can be combined for transfer to…

Cited by 12Source ↗PDF ↗Scholar ↗
2023

In-context Reinforcement Learning with Algorithm Distillation

Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald +8
ICLR 2023top-5%

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to reinforcement learn as an across-episode sequential prediction prob…

Cited by 145Source ↗PDF ↗Scholar ↗
2022

Model-Value Inconsistency as a Signal for Epistemic Uncertainty

Angelos Filos, Eszter Vértes, Zita Marinho, Gregory Farquhar, Diana Borsa, Abram Friesen +4
ICML 2022spotlight

Using a model of the environment and a value function, an agent can construct many estimates of a state’s value, by unrolling the model for different lengths and bootstrapping with its value function. Our key insight is that one can treat this set of value estimates as a type of ensemble, which we c…

Cited by 11Source ↗PDF ↗Scholar ↗
2021

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Neil Band, Tim G. J. Rudner, Qixuan Feng, Angelos Filos, Zachary Nado, Michael W Dusenberry +3
NeurIPS 2021poster

Bayesian deep learning seeks to equip deep neural networks with the ability to precisely quantify their predictive uncertainty, and has promised to make deep learning more reliable for safety-critical real-world applications. Yet, existing Bayesian deep learning methods fall short of this promise; n…

Cited by 59Source ↗Scholar ↗
2021

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

Angelos Filos, Clare Lyle, Yarin Gal, Sergey Levine, Natasha Jaques, Gregory Farquhar
ICML 2021oral

We study reinforcement learning (RL) with no-reward demonstrations, a setting in which an RL agent has access to additional data from the interaction of other agents with the same environment. However, it has no access to the rewards or goals of these agents, and their objectives and levels of exper…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2021

Self-Consistent Models and Values

Gregory Farquhar, Kate Baumli, Zita Marinho, Angelos Filos, Matteo Hessel, Hado van Hasselt +1
NeurIPS 2021poster

Learned models of the environment provide reinforcement learning (RL) agents with flexible ways of making predictions about the environment. Models enable planning, i.e. using more computation to improve value functions or policies, without requiring additional environment interactions. In this work…

Cited by 14Source ↗PDF ↗Scholar ↗
2020

Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?

Angelos Filos, Panagiotis Tigkas, Rowan Mcallister, Nicholas Rhinehart, Sergey Levine, Yarin Gal
ICML 2020poster

Out-of-training-distribution (OOD) scenarios are a common challenge of learning agents at deployment, typically leading to arbitrary deductions and poorly-informed decisions. In principle, detection of and adaptation to OOD scenes can mitigate their adverse effects. In this paper, we highlight the l…

Cited by 245Source ↗PDF ↗code ↗Scholar ↗
2020

Invariant Causal Prediction for Block MDPs

Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau +2
ICML 2020poster

Generalization across environments is critical to the successful application of reinforcement learning (RL) algorithms to real-world challenges. In this work we propose a method for learning state abstractions which generalize to novel observation distributions in the multi-environment RL setting. W…

Cited by 169Source ↗PDF ↗code ↗Scholar ↗