paper-with-me

Papers

Generalization of Reinforcement Learners with Working and Episodic Memory

2019-10-29 · NeurIPS 2019 12 · Meire Fortunato, Melissa Tan, Ryan Faulkner, Steven Hansen, Adrià Puigdomènech Badia, Gavin Buttimore, Charlie Deck, Joel Z. Leibo, Charles Blundell

Memory is an important aspect of intelligence and plays a role in many deep reinforcement learning models. However, little progress has been made in understanding when specific memory systems help more than others and how well they generalize. The field also has yet to see a prevalent consistent and rigorous approach for evaluating agent performance on holdout data. In this paper, we aim to develop a comprehensive methodology to test different kinds of memory in an agent and assess how well the agent can apply what it learns in training to a holdout set that differs from the training set along dimensions that we suggest are relevant for evaluating memory-specific generalization. To that end, we first construct a diverse set of memory tasks that allow us to evaluate test-time generalization across multiple dimensions. Second, we develop and perform multiple ablations on an agent architecture that combines multiple memory systems, observe its baseline models, and investigate its performance against the task suite.

📄 PDF Abstract BibTeX arXiv:1910.13406

Code (1)

deepmind/dm_memorytasks 공식 구현

Tasks

Deep Reinforcement LearningHoldout SetReinforcement Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Transformers are Meta-Reinforcement Learners

2021-09-29 · Luckeciano Carvalho Melo

The transformer architecture and variants presented a remarkable success across many machine learning tasks in recent years. This success is intrinsically related to the capability of handling long sequences and the pres…

continuous-controlContinuous ControlMeta Reinforcement LearningOut-of-Distribution Generalization+3

Transformers are Meta-Reinforcement Learners

2022-06-14 · Luckeciano C. Melo

The transformer architecture and variants presented remarkable success across many machine learning tasks in recent years. This success is intrinsically related to the capability of handling long sequences and the presen…

continuous-controlContinuous ControlMeta Reinforcement LearningOut-of-Distribution Generalization+3

Flexible Prefrontal Control over Hippocampal Episodic Memory for Goal-Directed Generalization

2025-03-04 · Yicong Zheng, Nora Wolf, Charan Ranganath, Randall C. O'Reilly 외

Many tasks require flexibly modifying perception and behavior based on current goals. Humans can retrieve episodic memories from days to years ago, using them to contextualize and generalize behaviors across novel but st…

HippocampusRetrieval

Two-Memory Reinforcement Learning

2023-04-20 · Zhao Yang, Thomas. M. Moerland, Mike Preuss, Aske Plaat

While deep reinforcement learning has shown important empirical success, it tends to learn relatively slow due to slow propagation of rewards information and slow update of parametric neural networks. Non-parametric epis…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningRepresentation Learning+1

Is prioritized sweeping the better episodic control?

2017-11-20 · Johanni Brea

Episodic control has been proposed as a third approach to reinforcement learning, besides model-free and model-based control, by analogy with the three types of human memory. i.e. episodic, procedural and semantic memory…

Reinforcement Learning