no code implementations • 3 Nov 2023 • Gabriele Tiboni, Pascal Klink, Jan Peters, Tatiana Tommasi, Carlo D'Eramo, Georgia Chalvatzaki
Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL).
no code implementations • 25 Sep 2023 • Pascal Klink, Florian Wolf, Kai Ploeger, Jan Peters, Joni Pajarinen
Reinforcement Learning (RL) allows learning non-trivial robot control laws purely from data.
no code implementations • 25 Sep 2023 • Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen
In this work, we focus on framing curricula as interpolations between task distributions, which has previously been shown to be a viable approach to CRL.
no code implementations • 12 Jul 2023 • Jihao Andreas Lin, Joe Watson, Pascal Klink, Jan Peters
Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior.
no code implementations • 9 Jun 2023 • Tobias Niehues, Ulla Scheler, Pascal Klink
Curricula based on Absolute Learning Progress (ALP) have proven successful in different environments, but waste computation on repeating already learned behaviour in new tasks.
no code implementations • 2 Nov 2022 • Hany Abdulsamad, Peter Nickl, Pascal Klink, Jan Peters
We derive two efficient variational inference techniques to learn these representations and highlight the advantages of hierarchical infinite local regression models, such as dealing with non-smooth functions, mitigating catastrophic forgetting, and enabling parameter sharing and fast predictions.
no code implementations • 29 Sep 2021 • Pascal Klink, Haoyi Yang, Jan Peters, Joni Pajarinen
Experiments demonstrate that the resulting introduction of metric structure into the curriculum allows for a well-behaving non-parametric version of SPRL that leads to stable learning performance across tasks.
no code implementations • ICLR 2022 • Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen
This approach, which we refer to as boosted curriculum reinforcement learning (BCRL), has the benefit of naturally increasing the representativeness of the functional space by adding a new residual each time a new task is presented.
no code implementations • 29 Sep 2021 • Jihao Andreas Lin, Joe Watson, Pascal Klink, Jan Peters
Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior predictive distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior.
no code implementations • 22 Apr 2021 • Stephan Weigand, Pascal Klink, Jan Peters, Joni Pajarinen
Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems.
1 code implementation • 25 Feb 2021 • Pascal Klink, Hany Abdulsamad, Boris Belousov, Carlo D'Eramo, Jan Peters, Joni Pajarinen
Across machine learning, the use of curricula has shown strong empirical potential to improve learning from data by avoiding local optima of training objectives.
no code implementations • pproximateinference AABI Symposium 2021 • Joe Watson, Jihao Andreas Lin, Pascal Klink, Jan Peters
Neural linear models (NLM) and Gaussian processes (GP) are both examples of Bayesian linear regression on rich feature spaces.
1 code implementation • 10 Nov 2020 • Hany Abdulsamad, Peter Nickl, Pascal Klink, Jan Peters
Probabilistic regression techniques in control and robotics applications have to fulfill different criteria of data-driven adaptability, computational efficiency, scalability to high dimensions, and the capacity to deal with different modalities in the data.
1 code implementation • NeurIPS 2020 • Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen
Curriculum reinforcement learning (CRL) improves the learning speed and stability of an agent by exposing it to a tailored series of tasks throughout learning.
no code implementations • 1 Nov 2019 • Tuan Dam, Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen
Finally, we empirically demonstrate the effectiveness of our method in well-known MDP and POMDP benchmarks, showing significant improvement in performance and convergence speed w. r. t.
1 code implementation • 7 Oct 2019 • Pascal Klink, Hany Abdulsamad, Boris Belousov, Jan Peters
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots.