Training Reinforcement Learning Agents and Humans With Difficulty-Conditioned Generators

no code implementations • 4 Dec 2023 • Sidney Tio, Jimmy Ho, Pradeep Varakantham

We adapt Parameterized Environment Response Model (PERM), a method for training both Reinforcement Learning (RL) Agents and human learners in parameterized environments by directly modeling difficulty and ability.

reinforcement-learning Reinforcement Learning (RL)

Transferable Curricula through Difficulty Conditioned Generators

no code implementations • 22 Jun 2023 • Sidney Tio, Pradeep Varakantham

In this paper, we introduce a method named Parameterized Environment Response Model (PERM) that shows promising results in training RL agents in parameterized environments.

Reinforcement Learning (RL) Starcraft +1

Improving Multi-Agent Cooperation using Theory of Mind

no code implementations • 30 Jul 2020 • Terence X. Lim, Sidney Tio, Desmond C. Ong

Recent advances in Artificial Intelligence have produced agents that can beat human world champions at games like Go, Starcraft, and Dota2.

Starcraft