Continuous Monte Carlo Graph Search

1 code implementation • 4 Oct 2022 • Kalle Kujanpää, Amin Babadi, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen

To address this problem, we propose Continuous Monte Carlo Graph Search (CMCGS), an extension of MCTS to online planning in environments with continuous state and action spaces.

Continuous Control Decision Making

Learning Task-Agnostic Action Spaces for Movement Optimization

1 code implementation • 22 Sep 2020 • Amin Babadi, Michiel Van de Panne, C. Karen Liu, Perttu Hämäläinen

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.

Visualizing Movement Control Optimization Landscapes

no code implementations • 17 Sep 2019 • Perttu Hämäläinen, Juuso Toikka, Amin Babadi, C. Karen Liu

A large body of animation research focuses on optimization of movement control, either as action sequences or policy parameters.

Self-Imitation Learning of Locomotion Movements through Termination Curriculum

1 code implementation • 27 Jul 2019 • Amin Babadi, Kourosh Naderi, Perttu Hämäläinen

In this paper, we propose and evaluate a novel combination of techniques for accelerating the learning of stable locomotion movements through self-imitation learning of synthetic animations.

Imitation Learning

PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation

1 code implementation • 5 Oct 2018 • Perttu Hämäläinen, Amin Babadi, Xiaoxiao Ma, Jaakko Lehtinen

Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach.

Continuous Control Reinforcement Learning (RL)