Hybrid Reward Architecture for Reinforcement Learning

1 code implementation • NeurIPS 2017 • Harm van Seijen, Mehdi Fatemi, Joshua Romoff, Romain Laroche, Tavian Barnes, Jeffrey Tsang

One of the main challenges in reinforcement learning (RL) is generalisation.

reinforcement-learning Reinforcement Learning (RL) +1

The parametrized probabilistic finite-state transducer probe game player fingerprint model

no code implementations • 29 Jan 2014 • Jeffrey Tsang

Fingerprinting operators generate functional signatures of game players and are useful for their automated analysis independent of representation or encoding.