183 citations · 474 across the 18 of their papers we have counts for
6 papers · 1 filter
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Angelos Filos, Eszter Vértes, Zita Marinho +7
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…
Temporal Abstraction in Reinforcement Learning with the Successor Representation
Marlos C. Machado, Andre Barreto, Doina Precup +1
Reasoning at multiple levels of temporal abstraction is one of the key attributes of intelligence. In reinforcement learning, this is often modeled through temporally extended cour…
Proper Value Equivalence
Christopher Grimm, André Barreto, Gregory Farquhar +2
One of the main challenges in model-based reinforcement learning (RL) is to decide which aspects of the environment should be modeled. The value-equivalence (VE) principle proposes…
Discovering Diverse Nearly Optimal Policies with Successor Features
Tom Zahavy, Brendan O'Donoghue, Andre Barreto +3
Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of d…
Risk-Aware Transfer in Reinforcement Learning using Successor Features
Michael Gimelfarb, André Barreto, Scott Sanner +1
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer le…
Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning
Víctor Campos, Pablo Sprechmann, Steven Hansen +5
Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning. Knowledge acquired during an uns…