6 papers
Continuous Monte Carlo Graph Search
Kalle Kujanpää, Amin Babadi, Yi Zhao +3
Online planning is crucial for high performance in many complex sequential decision-making tasks. Monte Carlo Tree Search (MCTS) employs a principled mechanism for trading off expl…
Learning Task-Agnostic Action Spaces for Movement Optimization
Amin Babadi, Michiel van de Panne, C. Karen Liu +1
We propose a novel method for exploring the dynamics of physically based animated characters, and learning a task-agnostic action space that makes movement optimization easier. Lik…
Visualizing Movement Control Optimization Landscapes
Perttu Hämäläinen, Juuso Toikka, Amin Babadi +1
A large body of animation research focuses on optimization of movement control, either as action sequences or policy parameters. However, as closed-form expressions of the objectiv…
Self-Imitation Learning of Locomotion Movements through Termination Curriculum
Amin Babadi, Kourosh Naderi, Perttu Hämäläinen
Animation and machine learning research have shown great advancements in the past decade, leading to robust and powerful methods for learning complex physically-based animations. H…
PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation
Perttu Hämäläinen, Amin Babadi, Xiaoxiao Ma +1
Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely s…
Intelligent Middle-Level Game Control
Amin Babadi, Kourosh Naderi, Perttu Hämäläinen
We propose the concept of intelligent middle-level game control, which lies on a continuum of control abstraction levels between the following two dual opposites: 1) high-level con…