Study how actions affect perception in embodied agents using group theory.
problem Understanding how actions influence perception in autonomous agents.
method Mathematical formalism of group theory applied to sensory commutativity of action sequences.
result Introduced Sensory Commutativity Probability (SCP) to measure action effects on perception.
Simple changes in neural activations can greatly affect task learning and switching.
problem How to learn and switch between new tasks quickly and flexibly.
method Investigated module architectures in an embodied two-dimensional touchscreen environment.
result Simple changes in neural activations significantly influence task learning and switching.
VALAN is a framework for navigation agents in photo-realistic environments.
problem Developing agents for indoor navigation tasks.
method Deep reinforcement learning with SEED RL architecture.
result VALAN framework can solve a variety of RL problems.
New approach categorizes objective functions for embodied agents.
problem Understanding how objectives relate to each other and discovering new objectives.
method Introducing Action Perception Divergence (APD) to categorize objective functions.
result Introduces a spectrum of objectives from narrow to general, explaining various unsupervised objectives.
Generative Multisensory Network learns 3D scene representations from multiple modalities.
problem Learning robust 3D scene representations from multiple sensory modalities.
method Amortized Product-of-Experts for efficient inference and cross-modal generation.
result The model can infer modality-invariant 3D scene representations efficiently from various sensory modalities.
Unified framework for imitating tasks across domains with discrepancies.
problem Learning tasks across domains with embodiment, viewpoint, and dynamics mismatches.
method Two-step approach: alignment followed by adaptation. Alignment uses Generative Adversarial MDP Alignment (GAMA) for state and action correspondences from unpaired, unaligned demonstrations. Adaptation leverages these correspondences for zero-shot imitation.
result Effectiveness of the proposed approach in embodiment, viewpoint, and dynamics mismatch scenarios.
Model learns multiple tasks using visual and textual representations.
problem Training visual navigation agents for multiple tasks.
method Dual-Attention unit for task-invariant alignment of visual and textual representations.
result Model outperforms baselines on semantic goal navigation and embodied question answering.
HRL4IN tackles interactive navigation tasks with mobile manipulators, improving efficiency and performance.
problem Interactive Navigation tasks require mobile manipulators to perform various actions, but choosing the right part of the embodiment is inefficient.
method HRL4IN uses a hierarchical reinforcement learning architecture to handle heterogeneous phases of navigation and manipulation, selecting the appropriate part of the embodiment for each phase.
result HRL4IN significantly outperforms flat PPO and HAC in terms of task performance and energy efficiency.
SMT improves robotic long-horizon tasks by embedding and utilizing past observations.
problem Long-horizon tasks in partially observable environments require effective long-term memory.
method Scene Memory Transformer (SMT) embeds and uses attention to exploit spatio-temporal dependencies.
result SMT outperforms existing policies in visual navigation tasks.
New sensor placement affects robot controller learnability.
problem Catastrophic forgetting in neural controllers for robots.
method Demonstrated how sensor placement alters loss function manifolds.
result Sensor placement can reduce or induce catastrophic forgetting.
Teacher algorithm helps DRL learn diverse environments efficiently.
problem Teach DRL to learn in various, unknown environments efficiently.
method Transformed into a bandit problem, learns to sample environments.
result ALP-GMM models learning progress, improving curriculum design.
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
problem Challenges in data efficiency, obstacle avoidance, and generalization in 3D visual navigation.
method Incorporates attention on 3D spatial relationships and a target skill extension module into DRL framework.
result Significantly improves navigation performance and generalization across targets and scenes.
Agents learn to draw with human-like abstraction and realism.
problem Training generative models to produce realistic images without supervision.
method Reinforcement learning agents in a simulated painting environment, trained with a discriminator network.
result Generative agents can produce images with visual abstraction and realism.
Algorithm integrates uncertainty for lifelong learning in dynamic environments.
problem Continuous, lifelong learning for intelligent agents in changing conditions.
method Inspired by neuromodulatory mechanisms, integrates uncertainty for self-supervised and one-shot learning.
result Stable learning without catastrophic forgetting in a virtual environment.
New text-to-image diffusion models improve scene understanding for AI agents.
problem Fine-grained scene understanding for AI agents from text and images.
method Pre-trained text-to-image diffusion models optimized for generating images from text prompts.
result Policies learned with Stable Control Representations outperform state-of-the-art approaches on various control tasks.
Low-dimensional vectors improve semantic understanding of music and language.
problem Noise in shared semantics due to individual brain biases.
method Jointly model multiple brains to learn low-dimensional vector embeddings.
result These embeddings outperform high-dimensional fMRI data in music and language classification.
Robot learns multiple tasks hierarchically by transferring knowledge.
problem Learning multiple complex tasks in open-ended environments.
method Task-oriented procedures, goal-babbling, imitation learning, active learning, intrinsic motivation.
result Robots can learn complex tasks more efficiently by transferring knowledge from simpler ones.
Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landsc…
Competition aims to develop sample-efficient RL methods using human demonstrations.
problem Exponential increase in samples needed for reinforcement learning.
method Develop sample-efficient algorithms using human demonstrations.
result Introduction of MineRL ObtainDiamond task and MineRL-v0 dataset.
This paper proposes a new method to connect language and physical actions in reinforcement learning.
problem Connecting linguistic representations to the physical world in embodied agents.
method Language-conditioned goal generators to decouple sensorimotor learning from language acquisition.
result Agents can demonstrate a diversity of behaviors for any given instruction.
New metric solves correspondence problem for robotic arm imitation learning.
problem Establishing corresponding states and actions between different robotic arms.
method Introducing a distance measure between dissimilar robotic arms and using it as a loss function.
result The distance measure effectively learns imitation policies by minimizing distance between robotic arms.
EDGI improves sample efficiency and generalization in tasks with spatial and temporal symmetries.
problem Sample inefficiency and poor generalization in tasks with geometric symmetries.
method Equivariant Diffuser framework, SE(3)xZxSn-equivariant diffusion model.
result EDGI is more sample efficient and generalizes better than non-equivariant models.
AIF improves physical AI agents' performance in dynamic environments.
problem Physical AI agents are less capable than biological agents in open-ended real-world environments.
method Developed from probability theory, Bayesian machine learning, variational inference, and Active Inference (AIF), grounded in the Free Energy Principle.
result AIF minimizes variational free energy and is well-suited to physical constraints.
Modeling social conventions from real-time interactions and sensorimotor control.
problem The role of real-time control and learning in social convention formation.
method Control-based Reinforcement Learning (CRL) model grounded in Distributed Adaptive Control (DAC) theory.
result CRL model achieves human-level performance in multi-agent game-theoretic tasks.
DIVA generates diverse tasks for complex simulators, enabling adaptive agent training.
problem Lack of diverse training data for complex, open-ended simulators.
method Evolutionary approach using domain randomization and procedural generation.
result Successfully trains adaptive agent behavior in complex simulators.
New RL method learns from passive data by modeling intentions.
problem Learning from passive data like videos without rewards or actions.
method Model intentions using temporal difference learning, learning representations from raw data.
result Successfully learns features from passive data that accelerate downstream RL tasks.
The paper introduces affordances for reinforcement learning, improving planning and learning efficiency.
problem Reinforcement learning assumes all actions are available, but real-world agents face limited action spaces.
method Developed a theory of affordances for Markov Decision Processes, proposing methods to learn and use affordances.
result Affordances improve planning speed and learning efficiency, leading to simpler and better generalizing transition models.
We study financial distributions within the framework of the continuous time random walk (CTRW). We review earlier approaches and present new results related to overnight effects as well as the generalization of the formalism which embodies a non-Markovian formulation of the CTRW aimed to account for correlated increme…
Paper proves Toponogov's theorem in Alexandrov geometry.
problem Proving Toponogov's theorem in Alexandrov geometry with lower curvature bound.
method Inspired by Riemannian geometry, uses second variation formula.
result Elementary proof of Toponogov's theorem in Alexandrov geometry.
New framework for AI to learn causal models through experience.
problem Lack of guidance for variable choice and interventions in causal models for AI.
method Defines actions as state space transformations, introduces causal variables, and identifies interventions.
result Clarifies the concept of interventions and makes causal representation learning clearer.
Paper introduces rehearsal-free continual learning for small, non-i.i.d. batches in robotic vision.
problem Learning new objects and improving recognition in a changing robotic environment.
method Two rehearsal-free continual learning techniques (CWR* and AR1*) for small, non-i.i.d. batches.
result AR1* outperforms other techniques by more than 15% in some cases.
We construct an elementary, combinatorial kind of topological quantum field theory, based on curves, surfaces, and orientations. The construction derives from contact invariants in sutured Floer homology and is essentially an elaboration of a TQFT defined by Honda--Kazez--Matic. This topological field theory stores inf…
Econophysics embodies the recent upsurge of interest by physicists into financial economics, driven by the availability of large amount of data, job shortage in physics and the possibility of applying many-body techniques developed in statistical and theoretical physics to the understanding of the self-organizing econo…
Agent learns to interpret 3D instructions, generalizing from experience.
problem Grounded language learning in artificial agents.
method Simulated 3D environment, reinforcement and unsupervised learning.
result Agent learns to relate language to physical surroundings and actions.
FinRL automates trading in quantitative finance with deep reinforcement learning.
problem Steep development curve for traders to automate trading decisions.
method Open-source framework implementing DRL algorithms and reward functions.
result FinRL simplifies strategy design and reduces debugging workloads.
Crowdsourced predictions from microservices improve supply chain efficiency.
problem Improving supply chain efficiency through high-quality predictions.
method Trials of a multi-agent system with microservices and economic incentives.
result Empirical lessons suggest potential for a Prediction Web.
Robot learns from human actions to perform complex tasks.
problem Learning complex skills from interaction data with embodiment differences.
method Formulated graphical model, treated action as observed variable, used domain-dependent prior.
result Robotic planning agent can learn tool use from human observations.
Multiple Kernel Learning (MKL) is used to replicate the signal combination process that trading rules embody when they aggregate multiple sources of financial information when predicting an asset's price movements. A set of financially motivated kernels is constructed for the EURUSD currency pair and is used to predict…
Three perspectives on quantizing magnetic Poisson structures are explored.
problem Quantization of magnetic Poisson structures with non-associativity.
method Deformation quantization, symplectic realization, geometric quantization using bundle gerbes.
result Comparison and contrast of different quantization approaches.
Commissioned by MIT's in-house artist Jane Philbrick, we evolve an abstract 2D surface (resembling Marta Pan's 1961 "Sculpture Flottante I") under mean curvature, all the while calculating the eigenmodes and eigenvalues of the Laplace-Beltrami operator on the resulting shapes. These are then synthesized into a sound-wa…
We use the mapping cone for the relative deRham cohomology of a manifold with boundary in order to show that the Chern-Gauss-Bonnet Theorem for oriented Riemannian vector bundles over such manifolds is a manifestation of Lefschetz Duality in any of the two embodiments of the latter. We explain how Thom isomorphism fits…
Federated learning collaborates clients to train models without sharing data.
problem Privacy and data sharing in machine learning.
method Central server orchestrates collaborative training of models on decentralized data.
result Recent advances and open problems in FL.
Integral formulae for foliated Riemannian manifolds provide obstructions for existence of foliations or compact leaves of them with given geometric properties. Recently, we associated a new Riemannian metric to a codimension-one foliated Finsler space and proved integral formulae for general and for Randers spaces. In …
We introduce a conceptually novel structured prediction model, GPstruct, which is kernelized, non-parametric and Bayesian, by design. We motivate the model with respect to existing approaches, among others, conditional random fields (CRFs), maximum margin Markov networks (M3N), and structured support vector machines (S…
A new approach to group fairness treats it as a bargaining problem.
problem Fairness in deploying predictors across subpopulations.
method Interpreting fairness as a bargaining problem and proposing relative improvement.
result Relative improvement provides axiomatic justification and finite-sample convergence guarantees.
In recent years, manifold learning has become increasingly popular as a tool for performing non-linear dimensionality reduction. This has led to the development of numerous algorithms of varying degrees of complexity that aim to recover man ifold geometry using either local or global features of the data. Building on t…
PBN combines generative and discriminative capabilities in a neural network.
problem Combining generative and discriminative capabilities in neural networks.
method Convolutional PBN, sharing FF-NN embodiment, combining generative and discriminative qualities.
result PBN shows excellent qualities from either generative or discriminative viewpoint.
Proposes a new method to enhance neural learning by maximizing information gain.
problem Improving neural learning by selecting key variables to maximize information gain.
method Adaptive Ensemble Kalman Filter to quantify uncertainty and maximize information gain.
result The proposed method enables the neural network to learn more effectively from stochastic systems.