paper-with-me

Papers

Expert-augmented actor-critic for ViZDoom and Montezumas Revenge

2018-09-10 · Michał Garmulewicz, Henryk Michalewski, Piotr Miłoś

We propose an expert-augmented actor-critic algorithm, which we evaluate on two environments with sparse rewards: Montezumas Revenge and a demanding maze from the ViZDoom suite. In the case of Montezumas Revenge, an agent trained with our method achieves very good results consistently scoring above 27,000 points (in many experiments beating the first world). With an appropriate choice of hyperparameters, our algorithm surpasses the performance of the expert data. In a number of experiments, we have observed an unreported bug in Montezumas Revenge which allowed the agent to score more than 800,000 points.

📄 PDF Abstract BibTeX arXiv:1809.03447

Code (2)

ghostFaceKillah/expert 공식 구현 tf
monte-ai/expert-augmented-acktr tf

Similar Papers 제목 키워드 기반

Capsule Network Performance with Autonomous Navigation

2020-02-08 · Thomas Molnar, Eugenio Culurciello

Capsule Networks (CapsNets) have been proposed as an alternative to Convolutional Neural Networks (CNNs). This paper showcases how CapsNets are more capable than CNNs for autonomous agent exploration of realistic scenari…

Autonomous NavigationReinforcement Learning

Robust Dual View Deep Agent

2018-04-13 · Ibrahim M. Sobh, Nevin M. Darwish

Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Self-Imitation Learning via Trajectory-Conditioned Policy for Hard-Exploration Tasks

2019-09-25 · Yijie Guo, Jongwook Choi, Marcin Moczulski, Samy Bengio 외

Imitation learning from human-expert demonstrations has been shown to be greatly helpful for challenging reinforcement learning problems with sparse environment rewards. However, it is very difficult to achieve similar s…

Imitation Learning

Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems

2021-07-05 · Shashank Hegde, Anssi Kanervisto, Aleksei Petrenko

Humans and other intelligent animals evolved highly sophisticated perception systems that combine multiple sensory modalities. On the other hand, state-of-the-art artificial agents rely mostly on visual inputs or structu…

Game of Doomreinforcement-learningReinforcement Learning (RL)Vocal Bursts Intensity Prediction

STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack

2024-10-14 · Naman Gupta, Shashank Kirtania, Priyanshu Gupta, Krishna Kariya 외

Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external kn…

RAGRetrievalRetrieval-augmented Generation