activity
20152021
most citedAnalysing Congestion Problems in Multi-agent Reinforcement Learning

6 citations · 21 across the 8 of their papers we have counts for

collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI20213 cited

Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning

Youri Coppens, Denis Steckelmacher, Catholijn M. Jonker +1

Today's advanced Reinforcement Learning algorithms produce black-box policies, that are often difficult to interpret and trust for a person. We introduce a policy distilling algori…

cs.AI20191 cited

Transfer Learning Across Simulated Robots With Different Sensors

Hélène Plisnier, Denis Steckelmacher, Diederik Roijers +1

For a robot to learn a good policy, it often requires expensive equipment (such as sophisticated sensors) and a prepared training environment conducive to learning. However, it is…

cs.AI20193 cited

The Actor-Advisor: Policy Gradient With Off-Policy Advice

Hélène Plisnier, Denis Steckelmacher, Diederik M. Roijers +1

Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the…

cs.AI2017

Learning with Options that Terminate Off-Policy

Anna Harutyunyan, Peter Vrancx, Pierre-Luc Bacon +2

A temporally abstract action, or an option, is specified by a policy and a termination condition: the policy guides option behavior, and the termination condition roughly determine…

cs.AI2017

Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets

Denis Steckelmacher, Diederik M. Roijers, Anna Harutyunyan +3

Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are us…

cs.AI20154 cited

Off-Policy Reward Shaping with Ensembles

Anna Harutyunyan, Tim Brys, Peter Vrancx +1

Potential-based reward shaping (PBRS) is an effective and popular technique to speed up reinforcement learning by leveraging domain knowledge. While PBRS is proven to always preser…