SF-DQN improves RL transfer by learning successor features.
problem Transfer RL with shared dynamics but different reward functions.
method Decomposes Q-function into SF and reward mapping; uses GPI for policy improvement.
result SF-DQN with GPI converges faster and generalizes better than traditional RL methods.
New algorithm learns expert reward structures from batch data.
problem Learning expert reward structures from batch data without dynamics models.
method Deep Successor Feature Networks (DSFN) and transition-regularized imitation network.
result Superior performance on control benchmarks and sepsis management.
A model learns successor representations in uncertain environments.
problem Learning effective strategies in partially observable, noisy environments.
method Neurally plausible model using distributional successor features.
result Distributional successor features support reinforcement learning in noisy environments.
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation…
Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor ma…
VISR learns controllable features for fast task inference.
problem Generalizing behaviors beyond explicitly learned set for subsequent tasks.
method Combines Successor Features and Variational Inference.
result Achieves human-level performance on 14 Atari games.
VUSFA improves transfer learning for target-driven navigation in AI2THOR.
problem Improving transfer reinforcement learning for complex visual navigation tasks.
method Introducing SFDP and Variational Information Bottlenecks to A3C agent.
result VUSFA achieves state-of-the-art performance and generalizability.
Proto-value networks improve deep reinforcement learning representations using auxiliary tasks.
problem Improving deep reinforcement learning representations with auxiliary tasks.
method Derived a new family of auxiliary tasks based on the successor measure, combined with off-policy learning rule.
result Proto-value networks produce rich features comparable to established algorithms using only linear approximation and a small number of interactions.
In this paper we introduce a simple approach for exploration in reinforcement learning (RL) that allows us to develop theoretically justified algorithms in the tabular case but that is also extendable to settings where function approximation is required. Our approach is based on the successor representation (SR), which…
Deep RL approach improves MIS for complex environments.
problem Improving off-policy evaluation for complex environments.
method Uses successor representation from deep RL to decouple reward and dynamics.
result Empirically stable and applicable to high-dimensional domains.
A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring knowledge between tasks with shared transition dynamics. This paper presents Model Featu…
USFs capture dynamics for faster RL task transfer.
problem Applying knowledge from one task to another.
method Proposed Universal Successor Features (USFs) for RL.
result USFs accelerate training and transfer knowledge.
Proposes method to discover diverse near-optimal policies in reinforcement learning.
problem Finding different solutions to the same problem in reinforcement learning.
method Formalizes problem as CMDP, uses Successor Features, proposes new diversity rewards.
result Proposed method discovers diverse near-optimal policies that are robust and distinct.
State2vec improves RL by learning state embeddings that generalize across policies.
problem Inefficient generalization across policies in RL.
method Extends node2vec to learn state embeddings accounting for discounted future state transitions.
result Captures the geometry of the state space, leading to sample-efficient value function approximation.
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which can…
The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills. We focus on one aspect in particular, namely the ability…
Successor Options discovers reusable skills using landmark states.
problem Discovering reusable skills in reinforcement learning.
method Leverages Successor Representations to build a state space model and learns intra-option policies using a novel pseudo-reward.
result Demonstrates the approach's efficacy on grid-worlds and high-dimensional robotic control environments.
Identifies optimal base features for zero-shot adaptation in reinforcement learning.
problem Unclear what constitutes a good set of base features for a wide range of downstream tasks.
method Identifies optimal base features based on downstream performance, without assuming downstream tasks are linear.
result Optimal base features are the same across three task families, differing from Laplacian eigenfunctions.
Paper introduces a new distributional successor measure for reinforcement learning.
problem Learning the distributional consequences of behavior in reinforcement learning.
method Formulates distributional successor measure as a distribution over distributions, proposes algorithm to learn it from data.
result Demonstrates zero-shot risk-sensitive policy evaluation.
New framework for efficient query-based imitation learning.
problem Aligning agent policy with human expert behavior without prior knowledge.
method Adversarial reward query with successor representation.
result Significantly outperforms uncertainty-based methods in query efficiency.
CAST predicts distribution-valued time series by stabilizing and transporting simplex-supported successors.
problem Forecasting distribution-valued time series with structural failure modes.
method CAST (Causal Anchored Simplex Transport) uses successors retrieved from causal context, stabilized with a persistence anchor, and locally transported on ordered supports.
result CAST outperforms baselines on eleven public and simulated benchmarks, achieving best average rank on both one-step KL and autoregressive rollout JSD.
In classical curve theory, the geometry of a curve in three dimensions is essentially characterized by their invariants, curvature and torsion. When they are given, the problem of finding a corresponding curve is known as 'solving natural equations'. Explicit solutions are known only for a handful of curve classes, inc…
Paper proposes a new method for efficient exploration in reinforcement learning.
problem Sparse reward reinforcement learning challenges in exploration.
method Learn separate intrinsic and extrinsic task policies, schedule between them, and use successor feature control (SFC).
result Substantially improved exploration efficiency with SFC and hierarchical usage of intrinsic drives.
This research formalizes inductive generalization and proposes a new learning paradigm called Inductive Learning.
problem Generalization from easy to hard tasks, especially out-of-domain generalization.
method Formalizes inductive generalization, introduces Inductive Learning, and outlines steps to adapt techniques for learning model successors.
result A new learning paradigm (Inductive Learning) that emphasizes induction and universal properties of learning and computation.
Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning. Randomised value functions (RVF) can be viewed as a promising approach to scaling PSRL. However, we show that most contemporary algorithms combining RVF with neural network f…
The paper shows how neural networks can approximate PDEs with polynomial scaling in dimension.
problem Understanding the complexity of approximating PDE solutions with neural networks.
method Developed a proof technique to simulate gradient descent using neural networks.
result Neural network parameters scale polynomially with input dimension for approximating PDE solutions.
Hybrid deep learning model predicts urban floods with high accuracy.
problem Urban flood prediction and situation awareness using channel network sensors data.
method FastGRNN-FCN hybrid deep learning model trained on Harris County, Texas flood data.
result Test accuracy and F-measure reach 97.8% and 0.792, respectively.
Tab-TRM uses recursive model for insurance pricing on tabular data.
problem Insurance pricing on tabular data.
method Adapts recursive latent reasoning to insurance modeling using a compact, parameter-efficient network.
result Improves insurance pricing accuracy using iterative refinement of latent tokens.
Algorithm improves transfer learning by inferring successor maps.
problem Machine learning challenges in multi-task scenarios.
method Combining factorized representations and nonparametric memory-based approaches.
result Improves transfer capabilities and outperforms other algorithms.
In classical curve theory, the geometry of a curve in three dimensions is essentially characterized by their invariants, curvature and torsion. When they are given, the problem of finding a corresponding curve is known as 'solving natural equations'. Explicit solutions are known only for a handful of curve classes, inc…
Our work proves CSF can recover ground-truth features in RL, improving understanding of feature learning.
problem Understanding the role of representation and mutual information in reinforcement learning.
method Investigates Contrastive Successor Features (CSF) method for identifiable representation learning in reinforcement learning.
result Proves CSF can recover ground-truth features up to a linear transformation.
New method proves neural networks can select features consistently.
problem Feature selection for deep neural networks is challenging.
method Adaptive Group Lasso selection procedure with Group Lasso as the base estimator.
result Adaptive Group Lasso is selection-consistent for a wide class of neural networks.
ARMA cell simplifies neural autoregressive modeling for time series.
problem Complex RNN cells are not always necessary and can be inferior.
method Introduces ARMA cell, a simpler, modular approach for neural time series modeling.
result The ARMA cell is competitive with popular alternatives in performance.
Deep neural networks are a powerful tool for feature learning and extraction given their ability to model high-level abstractions in highly complex data. One area worth exploring in feature learning and extraction using deep neural networks is efficient neural connectivity formation for faster feature learning and extr…
The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus on the transfer scenario where the dynamics among tasks are the same, but their goals differ. Although general value function (Sutton et al., 2011) has been shown to be useful for k…
Proposes a new method to prevent overfitting in deep neural networks.
problem Overfitting in deep neural networks with many trainable parameters.
method Randomly replaces elements in feature maps with specific values during training.
result Improves the testing performance of deep neural networks on benchmark datasets.
Deep-gKnock uses DNNs to select groups of features with improved interpretability.
problem Feature selection in high-dimensional data with grouping structure.
method Combines deep neural networks with Knockoffs technique for group-feature selection.
result Improves interpretability and accurate gFDR control compared to state-of-the-art methods.
Study compares random and learned features in deep Bayesian linear models.
problem Understanding how feature learning affects generalization in deep learning.
method Comparing deep random feature models to deep networks with trained layers.
result Random feature models can display double-descent behavior, while deep networks do not.
Paper identifies how neural networks learn features.
problem Understanding how neural networks automatically select features.
method Deep Neural Feature Ansatz, implementing average gradient outer product.
result Recursive Feature Machines achieve state-of-the-art performance.
This paper shows overparameterized deep neural networks are convex and learn useful features.
problem Analyzing fully trained overparameterized deep neural networks.
method Generalized neural feature repopulation technique.
result Overparameterized deep neural networks are inherently convex and learn useful features.
Researchers quantify the relationship between feature depth and performance in deep neural networks.
problem Understanding how depth affects feature extraction and generalization in deep neural networks.
method Adaptive analysis of feature-depth trade-offs in deep nets, proving optimal generalization performance.
result Optimal generalization performance achieved through empirical risk minimization on deep nets.
Develops a new method for optimizing policies in hierarchical models.
problem Optimizing complex policies in hierarchical models.
method Applies second-order methods in the space of state-action paths.
result The natural path gradient method can be computed exactly and reflects state-space hierarchy.
This work presents deep asymmetric networks with a set of node-wise variant activation functions. The nodes' sensitivities are affected by activation function selections such that the nodes with smaller indices become increasingly more sensitive. As a result, features learned by the nodes are sorted by the node indices…
Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of size (both width and depth), activation function, and weight initialization on th…
This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additiona…
Characterizes test error in learning with deep, structured feature maps.
problem Characterizing test error in learning with deep, structured feature maps.
method Asymptotic analysis of feature covariance and population covariance.
result Closed-form formula for feature covariance in Gaussian rainbow neural networks.
Proposes a feature leveling method to improve interpretability of deep neural networks.
problem Deep neural networks are hard to interpret due to mixed feature levels.
method Introduces a feature leveling architecture to isolate low and high level features.
result Modified models achieve competitive results and improved interpretability.
Theory explains how deep nets learn features from data.
problem Understanding how deep neural networks learn features from data.
method Developed a noise-nonlinearity phase diagram and a mechanical theory.
result Links feature learning across layers to generalization.