Similar Links:

• Exploration Strategies in Deep Reinforcement Learning

• Unifying Count-Based Exploration and Intrinsic Motivation

• Observe and Look Further: Achieving Consistent Performance on Atari

• Exploration by Random Network Distillation

• Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment

• RND: Large-Scale Study of Curiosity-Driven Learning

• Computational mechanisms of curiosity and goal-directed exploration

• Towards Information-Seeking Agents

• Semantic Exploration from Language Abstractions and Pretrained Representations

• Language Reward Modulation for Pretraining Reinforcement Learning

• Large Language Models Think Too Fast To Explore Effectively

• Intelligent Go-Explore (IGE): Standing on the Shoulders of Giant Foundation Models

• Empowerment contributes to exploration behavior in a creative video game

• Asymmetric self-play for automatic goal discovery in robotic manipulation

• Adversarial Active Exploration for Inverse Dynamics Model Learning

• Metacontrol for Adaptive Imagination-Based Optimization

• Pitfalls of learning a reward function online

• The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

• AIXIjs: A Software Demo for General Reinforcement Learning

• Learning through human feedback [blog]

• Search: GS; Google; site