Deep Intrinsically Motivated Exploration In Continuous Control

Abstract

In continuous control, exploration is often performed through undirected strategies in which parameters of the networks or selected actions are perturbed by random noise. Although the deep setting of undirected exploration has been shown to improve the performance of on-policy methods, they introduce an excessive computational complexity and are known to fail in the off-policy setting. The intrinsically motivated exploration is an effective alternative to the undirected strategies, but they are usually studied for discrete action domains. In this paper, we investigate how intrinsic motivation can effectively be combined with deep reinforcement learning in the control of continuous systems to obtain a directed exploratory behavior. We adapt the existing theories on animal motivational systems into the reinforcement learning paradigm and introduce a novel and scalable directed exploration strategy. The introduced approach, motivated by the maximization of the value function's error, can

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysaglam2022deep

Related papers

• Learning Off-policy With Model-based Intrinsic Motivation For Active Online Exploration (2024)0.00
• Centralized Cooperative Exploration Policy For Continuous Control Tasks (2023)0.00
• Guided Exploration In Reinforcement Learning Via Monte Carlo Critic Optimization (2022)0.00
• Scheduled Intrinsic Drive: A Hierarchical Take On Intrinsically Motivated Exploration (2019)0.00
• Never Give Up: Learning Directed Exploration Strategies (2020)0.00
• Deep Exploration With Pac-bayes (2024)0.00
• Exploring More When It Needs In Deep Reinforcement Learning (2021)0.00
• Coordinated Exploration Via Intrinsic Rewards For Multi-agent Reinforcement Learning (2019)0.00