1 code implementation • 11 Dec 2021 • Vittorio La Barbera, Fabio Pardo, Yuval Tassa, Monica Daley, Christopher Richards, Petar Kormushev, John Hutchinson
Along with this model, we also provide a set of reinforcement learning tasks, including reference motion tracking, running, and neck control, used to infer muscle actuation patterns.
no code implementations • 27 Apr 2021 • Nemanja Rakicevic, Antoine Cully, Petar Kormushev
This paper proposes a novel method for diversity-based policy search via Neuroevolution, that leverages learned representations of the policy network parameters, by performing policy search in this learned representation space.
no code implementations • 15 Dec 2020 • Nemanja Rakicevic, Antoine Cully, Petar Kormushev
Our approach iteratively collects policies according to the QD framework, in order to (i) build a collection of diverse policies, (ii) use it to learn a latent representation of the policy parameters, (iii) perform policy search in the learned latent space.
1 code implementation • ICLR 2021 • Arash Tavakoli, Mehdi Fatemi, Petar Kormushev
To test this, we set forth the action hypergraph networks framework -- a class of functions for learning action representations in multi-dimensional discrete action spaces with a structural inductive bias.
no code implementations • 8 Aug 2019 • Roni Permana Saputra, Nemanja Rakicevic, Petar Kormushev
This network is trained to be able to detect a casualty using a point-cloud data input.
1 code implementation • 21 Feb 2019 • Nemanja Rakicevic, Petar Kormushev
We propose a novel active learning framework, consisting of decoupled task model and exploration components, which does not require an objective function.
no code implementations • 27 Nov 2018 • Arash Tavakoli, Vitaly Levdik, Riashat Islam, Christopher M. Smith, Petar Kormushev
We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution.
2 code implementations • ICLR 2019 • Fabio Pardo, Vitaly Levdik, Petar Kormushev
Being able to reach any desired location in the environment can be a valuable asset for an agent.
no code implementations • 5 Jul 2018 • Fabio Pardo, Vitaly Levdik, Petar Kormushev
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty.
1 code implementation • ICML 2018 • Fabio Pardo, Arash Tavakoli, Vitaly Levdik, Petar Kormushev
In case (ii), the time limits are not part of the environment and are only used to facilitate learning.
5 code implementations • 24 Nov 2017 • Arash Tavakoli, Fabio Pardo, Petar Kormushev
This approach achieves a linear increase of the number of network outputs with the number of degrees of freedom by allowing a level of independence for each individual action dimension.
no code implementations • 3 Jun 2017 • S. Reza Ahmadzadeh, Fulvio Mastrogiovanni, Petar Kormushev
A novel skill learning approach is proposed that allows a robot to acquire human-like visuospatial skills for object manipulation tasks.