On-device research index

arXiv research

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.

168,878 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “Sub-goals”

IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RLcs.LG

Framework discovers sub-goals for better exploration in RL tasks.

problem Improving exploration in sequential decision making under partial observability.

method Variational intrinsic control framework with information theoretic regularizer.

result Sub-goals discovered without explicit supervision lead to better exploration and sample efficiency.

RL Exploration Sub-goals Empowerment Information Theory

2019-07-24abs ↗pdf ↗

Sub-Goal Trees -- a Framework for Goal-Directed Trajectory Prediction and Optimizationcs.LG

A new trajectory representation method for AI problems.

problem Trajectory prediction and optimization in AI problems.

method Sub-goal trees, recursively partitioning trajectories into sub-segments.

result Sub-goal trees predict trajectories faster and more accurately.

trajectory prediction reinforcement learning sub-goal trees dynamic programming motion planning

2019-06-12abs ↗pdf ↗

Learning from Trajectories via Subgoal Discoverycs.LG

This paper proposes a method to learn from expert trajectories by decomposing tasks into sub-goals.

problem Learning complex goal-oriented tasks with sparse rewards and limited samples.

method The approach uses expert trajectories to decompose tasks into sub-goals, learning an extrinsic reward function and modulating sub-goal predictions.

result The method alleviates errors in imitation learning and solves complex tasks that other methods cannot.

trajectory learning sub-goals sparse rewards imitation learning reinforcement learning

2019-11-03abs ↗pdf ↗

Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planningcs.LG

Improves RL planning by proposing sub-goals hierarchically.

problem Sequential planning assumption in RL.

method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).

result Improves navigation and control tasks.

Monte Carlo Tree Search Reinforcement Learning Goal-Directed Planning Sub-Goal Proposals Hierarchical Planning

2020-04-23abs ↗pdf ↗

Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learningcs.LG

In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a good representation of sub-goals in the environment and a low-level policy that can…

2018-11-22abs ↗pdf ↗

Self-organization of action hierarchy and compositionality by reinforcement learning with recurrent neural networkscs.LG

Recurrent neural networks (RNNs) for reinforcement learning (RL) have shown distinct advantages, e.g., solving memory-dependent tasks and meta-learning. However, little effort has been spent on improving RNN architectures and on understanding the underlying neural mechanisms for performance gain. In this paper, we prop…

2019-01-29abs ↗pdf ↗

Third-Person Visual Imitation Learning via Decoupled Hierarchical Controllercs.LG

Agent learns third-person manipulation tasks from a single video.

problem Learning from third-person videos to perform novel tasks.

method Decoupling high-level task generation from low-level action prediction.

result Agent successfully learns and performs tasks in unseen scenarios.

imitation learning third-person robotic manipulation hierarchical control Baxter

2019-11-21abs ↗pdf ↗

Transferring Agent Behaviors from Videos via Motion GANscs.LG

A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances. We introduce a general mechanism for automatically specifying meaningful behaviors from raw pixels. In particular, we train a generative adversarial network to …

2017-11-21abs ↗pdf ↗

Fairness without Regretcs.LG

Optimizes fairness without sacrificing primary objectives.

problem Achieving fairness in optimization without reducing solution quality.

method Parametrized objective function to generate a set of optimal solutions, then optimize fairness using secondary criteria.

result Optimal solutions can be found that balance fairness and primary objectives.

fairness optimization regret parametrized objective societal cost

2019-07-11abs ↗pdf ↗

Hyperbolic Embeddings for Learning Options in Hierarchical Reinforcement Learningcs.LG

Hierarchical reinforcement learning deals with the problem of breaking down large tasks into meaningful sub-tasks. Autonomous discovery of these sub-tasks has remained a challenging problem. We propose a novel method of learning sub-tasks by combining paradigms of routing in computer networks and graph based skill disc…

2018-12-04abs ↗pdf ↗

Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transformmath.AT

Study reveals RL game's embedding space is stratified, not a manifold.

problem Understanding the structure of RL game embeddings.

method Adapted Robinson's volume growth transform for RL setting.

result Token embedding space is stratified, not a manifold.

Reinforcement Learning Volume Growth Transform Stratified Space Proximal Policy Optimization Coin Collecting Game

2025-07-29abs ↗pdf ↗