A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
HRM-Agent learns to navigate dynamic mazes using 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 reinforce…
This paper presents a problem of model learning for the purpose of learning how to navigate a ball to a goal state in a circular maze environment with two degrees of freedom. The motion of the ball in the maze environment is influenced by several non-linear effects such as dry friction and contacts, which are difficult…
Sparse reward is one of the biggest challenges in reinforcement learning (RL). In this paper, we propose a novel method called Generative Exploration and Exploitation (GENE) to overcome sparse reward. GENE automatically generates start states to encourage the agent to explore the environment and to exploit received rew…
Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture. Despite their effectiveness, they suffer from several disadvantages including training instability, random …
We present a recurrent neural network memory that uses sparse coding to create a combinatoric encoding of sequential inputs. Using several examples, we show that the network can associate distant causes and effects in a discrete stochastic process, predict partially-observable higher-order sequences, and enable a DQN a…
New algorithm minimizes FE objectives for synthetic AIF agents.
AC-State discovers minimal latent state for control.
Recent developments in deep reinforcement learning have enabled the creation of agents for solving a large variety of games given a visual input. These methods have been proven successful for 2D games, like the Atari games, or for simple tasks, like navigating in mazes. It is still an open question, how to address more…
Deep network solves maze path planning without training.
MAZE attacks a model without data, using synthetic inputs.
Max entropy exploration guides reinforcement learning agents to pursue achievable goals.
We propose a probabilistic framework to directly insert prior knowledge in reinforcement learning (RL) algorithms by defining the behaviour policy as a Bayesian posterior distribution. Such a posterior combines task specific information with prior knowledge, thus allowing to achieve transfer learning across tasks. The …
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is a…
The paper proposes a structure learning model for efficient reinforcement learning.
In this work, we present a reinforcement learning algorithm that can find a variety of policies (novel policies) for a task that is given by a task reward function. Our method does this by creating a second reward function that recognizes previously seen state sequences and rewards those by novelty, which is measured u…
AR CI framework handles complex confounders and sequential actions.
This work improves policy optimization by maximizing entropy of state distribution, leading to better exploration.
Logical neural networks solve mazes by filling dead ends, but not all methods generalize well.
Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy. However …
Improves deep RL agents' generalization to unseen environments.
SMiRL learns to minimize surprise in unstable environments, improving agent performance.
The design of gaits for robot locomotion can be a daunting process which requires significant expert knowledge and engineering. This process is even more challenging for robots that do not have an accurate physical model, such as compliant or micro-scale robots. Data-driven gait optimization provides an automated alter…
In this paper we approach two relevant deep learning topics: i) tackling of graph structured input data and ii) a better understanding and analysis of deep networks and related learning algorithms. With this in mind we focus on the topological classification of reachability in a particular subset of planar graphs (Maze…
Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to construct a plan. Here we introduce the "Imagination-based Planner", the first m…
PBCS combines RL and motion planning for better exploration.
Deep Reinforcement Learning has shown tremendous success in solving several games and tasks in robotics. However, unlike humans, it generally requires a lot of training instances. Trajectories imitating to solve the task at hand can help to increase sample-efficiency of deep RL methods. In this paper, we present a simp…
New RL approach builds short ancestral recombination graphs.
AutoDIME automates design of multi-agent environments for RL.
CSAC enables cooperative reinforcement learning for multi-stage tasks.
This study proposes hidden state curiosity to enhance RL models' resilience against noise.
UC-SSP algorithm tackles exploration in stochastic shortest path problems without loop-free assumption.
This paper introduces a new approach to active inference using constrained Bethe Free Energy.
Introduces a natural parallel translation for navigation data.
Challenge to separate Earth's magnetic field from vehicle's magnetic field for accurate navigation.
Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive N…
Navigation in Lorentz Finsler geometry induces isoparametric hypersurfaces.
VALAN is a framework for navigation agents in photo-realistic environments.
The paper solves navigation problems on conic Kropina manifolds and establishes curvature relationships.
Robotic navigation improves with RL and ultrasound images.
Improved robot navigation using multi-head attention for natural language instructions.
The problem of pursuing a moving target is always one of the main topics in navigation. In the literatures, there are two well-known algorithms called Pure Pursuit and Pure Rendezvous navigation in the 3-dimensional space . In this paper, these two methods are combined to introduce a novel family of pursu…
Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a nov…
SLAM-net learns to navigate visually in challenging indoor environments.
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
Bayesian model for energy consumption helps electric vehicles navigate efficiently.
This work analyzes minimum-time navigation on Riemannian manifolds using Finsler geometry.
ERM uses energy-based selection to improve recursive reasoning.