Oliver Richter
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Oliver Richter has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Roger Wattenhofer
ETH Zurich, Zurich, Switzerland
6 shared publications - Gino Brunner
Department of Electrical Engineering and Information Technology ETH Zurich Switzerland
2 shared publications - Jeremia Geiger
ETH Zurich
2 shared publications - Karolis Martinkus
ETH Zurich
2 shared publications Roger Wattenhofer
ETH Zurich
2 shared publications- Johannes Ackermann
Technical University of Munich Technical University of Munich Kyushu Institute of Technology RIKEN RIKEN The University of Tokyo
1 shared publication
Latest Publications
- Open Access
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 6, 5815-5823
Automating Rigid Origami Design
Electronic proceedings of IJCAI 2023
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 6, 5815-5823
Open AccessAutomating Rigid Origami Design
Electronic proceedings of IJCAI 2023
- Open Access
Automating Rigid Origami Design
Rigid origami has shown potential in large diversity of practical applications. However, current rigid origami crease pattern design mostly relies on known tessellations. This strongly limits the diversity and novelty of patterns that can be created. In this work, we build upon the recently developed principle of three units method to formulate rigid origami design as a discrete optimization problem, the rigid origami game. Our implementation allows for a simple definition of diverse objectives and thereby expands the potential of rigid origami further to optimized, application-specific crease patterns. We showcase the flexibility of our formulation through use of a diverse set of search methods in several illustrative case studies. We are not only able to construct various patterns that approximate given target shapes, but to also specify abstract, function-based rewards which result in novel, foldable and functional designs for everyday objects.
Open AccessAutomating Rigid Origami Design
Rigid origami has shown potential in large diversity of practical applications. However, current rigid origami crease pattern design mostly relies on known tessellations. This strongly limits the diversity and novelty of patterns that can be created. In this work, we build upon the recently developed principle of three units method to formulate rigid origami design as a discrete optimization problem, the rigid origami game. Our implementation allows for a simple definition of diverse objectives and thereby expands the potential of rigid origami further to optimized, application-specific crease patterns. We showcase the flexibility of our formulation through use of a diverse set of search methods in several illustrative case studies. We are not only able to construct various patterns that approximate given target shapes, but to also specify abstract, function-based rewards which result in novel, foldable and functional designs for everyday objects.
- 1 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 501-505
Learning Algorithms with Self-Play: A New Approach to the Distributed Directory Problem
Many deep learning methods have been proposed recently to learn algorithms for combinatorial problems. However, most approaches focus on either supervised/imitation learning (the target algorithm is known) or single agent reinforcement learning (the input distribution is fixed). In some cases, however, the input distribution scales combinatorially as well and cannot easily be fully represented in a concise data set. In this paper, we propose a self-play approach to learn a distributed directory protocol to coordinate concurrent requests to a shared mobile resource among a network of nodes. The self-play is between two agents – a request agent, which finds worst case request inputs – and a route agent, which finds an algorithm that works well on the proposed worst case inputs (and consequently, works well on most queries). We show that our self-play approach is successful in learning an algorithm that works well across diverse request sequences. The empirical performance of the learnt algorithms is within the best known theoretical bounds, and sometimes significantly better than the best known upper bounds.
- 1 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 501-505
Learning Algorithms with Self-Play: A New Approach to the Distributed Directory Problem
Many deep learning methods have been proposed recently to learn algorithms for combinatorial problems. However, most approaches focus on either supervised/imitation learning (the target algorithm is known) or single agent reinforcement learning (the input distribution is fixed). In some cases, however, the input distribution scales combinatorially as well and cannot easily be fully represented in a concise data set. In this paper, we propose a self-play approach to learn a distributed directory protocol to coordinate concurrent requests to a shared mobile resource among a network of nodes. The self-play is between two agents – a request agent, which finds worst case request inputs – and a route agent, which finds an algorithm that works well on the proposed worst case inputs (and consequently, works well on most queries). We show that our self-play approach is successful in learning an algorithm that works well across diverse request sequences. The empirical performance of the learnt algorithms is within the best known theoretical bounds, and sometimes significantly better than the best known upper bounds.
- 10 September 2021
- Published by Springer Nature
- p. 222-237
Unsupervised Task Clustering for Multi-task Reinforcement Learning
- 10 September 2021
- Published by Springer Nature
- p. 222-237
Unsupervised Task Clustering for Multi-task Reinforcement Learning
- Open Access
Normalized Attention Without Probability Cage
Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work we highlight the limitations of constraining attention weights to the probability simplex and the resulting convex hull of value vectors. We show that Transformers are sequence length dependent biased towards token isolation at initialization and contrast Transformers to simple max- and sum-pooling - two strong baselines rarely reported. We propose to replace the softmax in self-attention with normalization, yielding a hyperparameter and data-bias robust, generally applicable architecture. We support our insights with empirical results from more than 25,000 trained models. All results and implementations are made available.
Open AccessNormalized Attention Without Probability Cage
Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work we highlight the limitations of constraining attention weights to the probability simplex and the resulting convex hull of value vectors. We show that Transformers are sequence length dependent biased towards token isolation at initialization and contrast Transformers to simple max- and sum-pooling - two strong baselines rarely reported. We propose to replace the softmax in self-attention with normalization, yielding a hyperparameter and data-bias robust, generally applicable architecture. We support our insights with empirical results from more than 25,000 trained models. All results and implementations are made available.
- Open Access
Learning Policies through Quantile Regression
Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are limited by the scope of the chosen parametric probability distribution. We show that alternatively to the likelihood based policy gradient, a related objective can be optimized through advantage weighted quantile regression. Our approach models the policy implicitly in the network, which gives the agent the freedom to approximate any distribution in each action dimension, not limiting its capabilities to the commonly used unimodal Gaussian parameterization. This broader spectrum of policies makes our algorithm suitable for problems where Gaussian policies cannot fit the optimal policy. Moreover, our results on the MuJoCo physics simulator benchmarks are comparable or superior to state-of-the-art on-policy methods.
Open AccessLearning Policies through Quantile Regression
Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are limited by the scope of the chosen parametric probability distribution. We show that alternatively to the likelihood based policy gradient, a related objective can be optimized through advantage weighted quantile regression. Our approach models the policy implicitly in the network, which gives the agent the freedom to approximate any distribution in each action dimension, not limiting its capabilities to the commonly used unimodal Gaussian parameterization. This broader spectrum of policies makes our algorithm suitable for problems where Gaussian policies cannot fit the optimal policy. Moreover, our results on the MuJoCo physics simulator benchmarks are comparable or superior to state-of-the-art on-policy methods.
- Open Access
Teaching a Machine to Read Maps with Deep Reinforcement Learning
The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforcement learning agent to read a map in order to find the shortest way out of a random maze it has never seen before. Our system combines several state-of-the-art methods such as A3C and incorporates novel elements such as a recurrent localization cell. Our agent learns to localize itself based on 3D first person images and an approximate orientation angle. The agent generalizes well to bigger mazes, showing that it learned useful localization and navigation capabilities.
Open AccessTeaching a Machine to Read Maps with Deep Reinforcement Learning
The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforcement learning agent to read a map in order to find the shortest way out of a random maze it has never seen before. Our system combines several state-of-the-art methods such as A3C and incorporates novel elements such as a recurrent localization cell. Our agent learns to localize itself based on 3D first person images and an approximate orientation angle. The agent generalizes well to bigger mazes, showing that it learned useful localization and navigation capabilities.