Expert-augmented actor-critic for ViZDoom and Montezumas Revenge
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.
Code (2)
Similar Papers 제목 키워드 기반
Capsule Network Performance with Autonomous Navigation
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 LearningRobust Dual View Deep Agent
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
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 LearningAgents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems
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 PredictionSTACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data.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