Curious Exploration And Return-based Memory Restoration For Deep Reinforcement Learning

Abstract

Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and optimised behaviour. In this paper, we focus on training a single agent to score goals with binary success/failure reward function in Half Field Offense domain. As the major advantage of this research, the agent has no presumption about the environment which means it only follows the original formulation of reinforcement learning agents. The main challenge of using such a reward function is the high sparsity of positive reward signals. To address this problem, we use a simple prediction-based exploration strategy (called Curious Exploration) along with a Return-based Memory Restoration (RMR) technique which tends to remember more valuable memories. The proposed method can be utilized to train agents in environments with fairly complex state and action spac

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytafazzol2021curious

Related papers

• Curiosity-driven Multi-agent Exploration With Mixed Objectives (2022)0.00
• Never Explore Repeatedly In Multi-agent Reinforcement Learning (2023)0.00
• Coordinated Exploration Via Intrinsic Rewards For Multi-agent Reinforcement Learning (2019)0.00
• Never Give Up: Learning Directed Exploration Strategies (2020)0.00
• Self-supervised Exploration Via Temporal Inconsistency In Reinforcement Learning (2022)3.58
• Reward Prediction Error As An Exploration Objective In Deep RL (2019)2.26
• REMAX: Relational Representation For Multi-agent Exploration (2020)2.26
• Curiosity-driven Exploration In Sparse-reward Multi-agent Reinforcement Learning (2023)0.00