On Improving Deep Reinforcement Learning For Pomdps

Abstract

Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architecture called Action-specific Deep Recurrent Q-Network (ADRQN) to enhance learning performance in partially observable domains. Actions are encoded by a fully connected layer and coupled with a convolutional observation to form an action-observation pair. The time series of action-observation pairs are then integrated by an LSTM layer that learns latent states based on which a fully connected layer computes Q-values as in conventional Deep Q-Networks (DQNs). We demonstrate the effectiveness of our new architecture in several partially observable domains, including flickering Atari games.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhu2017on

Related papers

• Dynamic Deep-reinforcement-learning Algorithm In Partially Observable Markov Decision Processes (2023)0.00
• Learning Interpretable Policies In Hindsight-observable Pomdps Through Partially Supervised Reinforcement Learning (2024)2.26
• Reinforcement Learning Under Partial Observability Guided By Learned Environment Models (2022)6.34
• Deep Hierarchical Reinforcement Learning Algorithm In Partially Observable Markov Decision Processes (2018)12.87
• Perception-prediction-reaction Agents For Deep Reinforcement Learning (2020)0.00
• Real-time Recurrent Reinforcement Learning (2023)2.26
• Provably Efficient Reinforcement Learning In Partially Observable Dynamical Systems (2022)0.00
• Discriminative Particle Filter Reinforcement Learning For Complex Partial Observations (2020)0.00