paper-with-me

홈 › Papers

A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings

2021-04-17 · Eltayeb Ahmed, Luisa Zintgraf, Christian A. Schroeder de Witt, Nicolas Usunier

In this work we explore an auxiliary loss useful for reinforcement learning in environments where strong performing agents are required to be able to navigate a spatial environment. The auxiliary loss proposed is to minimize the classification error of a neural network classifier that predicts whether or not a pair of states sampled from the agents current episode trajectory are in order. The classifier takes as input a pair of states as well as the agent's memory. The motivation for this auxiliary loss is that there is a strong correlation with which of a pair of states is more recent in the agents episode trajectory and which of the two states is spatially closer to the agent. Our hypothesis is that learning features to answer this question encourages the agent to learn and internalize in memory representations of states that facilitate spatial reasoning. We tested this auxiliary loss on a navigation task in a gridworld and achieved 9.6% increase in accumulative episode reward compared to a strong baseline approach.

📄 PDF Abstract BibTeX arXiv:2104.08492

Code (0)

등록된 구현이 없습니다.

Tasks

NavigateSpatial Reasoning

Similar Papers 제목 키워드 기반

Future Prediction Can be a Strong Evidence of Good History Representation in Partially Observable Environments

2024-02-11 · Jeongyeol Kwon, Liu Yang, Robert Nowak, Josiah Hanna

Learning a good history representation is one of the core challenges of reinforcement learning (RL) in partially observable environments. Recent works have shown the advantages of various auxiliary tasks for facilitating…

Future predictionMemorizationPredictionreinforcement-learning+3

Next Embedding Prediction Makes World Models Stronger

2026-03-03 · George Bredis, Nikita Balagansky, Daniil Gavrilov, Ruslan Rakhimov arxiv

Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free MBRL agent that leverages a temporal tr…

Reinforcement LearningSpatial Reasoning

SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games

2026-03-29 · Adam Haile arxiv

In 2019, Google DeepMind released MuZero, a model-based reinforcement learning method that achieves strong results in perfect-information games by combining learned dynamics models with Monte Carlo Tree Search (MCTS). Ho…

Reinforcement Learning

Self-Supervised Relation Alignment for Scene Graph Generation

2023-02-02 · Bicheng Xu, Renjie Liao, Leonid Sigal

The goal of scene graph generation is to predict a graph from an input image, where nodes correspond to identified and localized objects and edges to their corresponding interaction predicates. Existing methods are train…

Graph GenerationRelationRelation PredictionScene Graph Generation

Unsupervised Object-Based Transition Models for 3D Partially Observable Environments

2021-03-08 · NeurIPS 2021 12 · Antonia Creswell, Rishabh Kabra, Chris Burgess, Murray Shanahan

We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objec…

Object