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.
This work improves understanding of reinforcement learning state representations.
State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. Learning such representations without supervision from rewards is a challenging open problem. We introduce a method that learns state…
Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact representation of such a state is beneficial to help robots grasp onto their environment …
Survey categorizes methods for learning state representations in reinforcement learning.
Intelligent agents can cope with sensory-rich environments by learning task-agnostic state abstractions. In this paper, we propose an algorithm to approximate causal states, which are the coarsest partition of the joint history of actions and observations in partially-observable Markov decision processes (POMDP). Our m…
New method learns high-quality Laplacian representations for reinforcement learning.
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using generic priors on the state characteristics. However, the diversity in appl…
Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the state are task relevant and thus reduce the dimensionality of the space to explore.…
Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation i…
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, …
New insights into state representations in RL help design better learning rules.
Paper learns meaningful state and action representations from MDP trajectories.
We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to …
Study cost-driven state representation learning for control from partial observations.
Improved RL for grasping in cluttered scenes using state representation learning.
Paper introduces SALE for better state-action learning in RL.
Graph-based state representation improves deep RL performance.
Unsupervised representation learning has succeeded with excellent results in many applications. It is an especially powerful tool to learn a good representation of environments with partial or noisy observations. In partially observable domains it is important for the representation to encode a belief state, a sufficie…
Tabular Q-Learning with learned state abstractions solves continuous control tasks.
Study learns state representations from observations for control, proving guarantees.
Proves error bounds for state representation in RL using graph spectral features.
We consider the problem of building a state representation model for control, in a continual learning setting. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge, and then use Reinforcement Learning on the resulting features for efficient policy …
The paper introduces a method to learn Markov state abstractions for reinforcement learning.
Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading account of the midbrain dopamine system and the basal ganglia in reinforcement learnin…
ReLEX algorithm improves RL efficiency by selecting optimal representations.
POLAR learns efficient data acquisition policies using pretrained belief representations.
SPEDER extracts state-action abstraction from dynamics for reinforcement learning.
New method improves reinforcement learning generalization.
Recurrent neural networks (RNNs) are a vital modeling technique that rely on internal states learned indirectly by optimization of a supervised, unsupervised, or reinforcement training loss. RNNs are used to model dynamic processes that are characterized by underlying latent states whose form is often unknown, precludi…
Simple object representations improve model-free RL performance.
Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been superseded by approaches based on self-supervision. In this work we show that progress in image generation qu…
A new method for estimating uncertainty in deep neural networks.
A method to train multi-agent reinforcement learning models without intrinsic rewards.
Unified approach for learning state representations from streaming data.
MuZero visualizes its internal representations to stabilize planning.
RISE framework unifies and improves time series learning with missing data.
Neural Physicist learns physical dynamics from images.
The paper shows how to stabilize off-policy reinforcement learning using specific state representations.
We consider the problem of learning low-dimensional representations for large-scale Markov chains. We formulate the task of representation learning as that of mapping the state space of the model to a low-dimensional state space, called the kernel space. The kernel space contains a set of meta states which are desired …
ETC learns minimal representations for reinforcement learning in POMDPs.
Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more…
Deep reinforcement-learning methods have achieved remarkable performance on challenging control tasks. Observations of the resulting behavior give the impression that the agent has constructed a generalized representation that supports insightful action decisions. We re-examine what is meant by generalization in RL, an…
The smallest eigenvectors of the graph Laplacian are well-known to provide a succinct representation of the geometry of a weighted graph. In reinforcement learning (RL), where the weighted graph may be interpreted as the state transition process induced by a behavior policy acting on the environment, approximating the …
Recurrent neural networks (RNNs) are an effective representation of control policies for a wide range of reinforcement and imitation learning problems. RNN policies, however, are particularly difficult to explain, understand, and analyze due to their use of continuous-valued memory vectors and observation features. In …
Method learns representations invariant to task-irrelevant details in reinforcement learning tasks.
A new method learns action representations for reinforcement learning.
BCRL learns a Bellman complete representation for offline RL policy evaluation.
Persona2vec learns multiple node roles in graphs.