Improving Deep Reinforcement Learning In Minecraft With Action Advice
2019 · Spencer Frazier, Mark Riedl
Abstract
Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly identical visual features. Minecraft is an exemplar of such an environment. We hypothesize that interactive machine learning IML, wherein human teachers play a direct role in training through demonstrations, critique, or action advice, may alleviate agent susceptibility to aliasing. However, interactive machine learning is only practical when the number of human interactions is limited, requiring a balance between human teacher effort and agent performance. We conduct experiments with two reinforcement learning algorithms which enable human teachers to give action advice, Feedback Arbitration and Newtonian Action Advice, under visual aliasing conditions. To assess potential cognitive load per advice type, we vary the accuracy and frequency of various hu
Authors
(none)
Tags
Stats
Related papers
- Explore, Exploit Or Listen: Combining Human Feedback And Policy Model To Speed Up Deep Reinforcement Learning In 3D Worlds (2017)0.00
- Multi-task Curriculum Learning In A Complex, Visual, Hard-exploration Domain: Minecraft (2021)0.00
- Juewu-mc: Playing Minecraft With Sample-efficient Hierarchical Reinforcement Learning (2021)0.00
- Improving Interactive Reinforcement Learning: What Makes A Good Teacher? (2019)11.19
- Improving Multimodal Interactive Agents With Reinforcement Learning From Human Feedback (2022)0.00
- Human AI Interaction Loop Training: New Approach For Interactive Reinforcement Learning (2020)0.00
- Towards Human-like RL: Taming Non-naturalistic Behavior In Deep RL Via Adaptive Behavioral Costs In 3D Games (2023)0.00
- Agent-aware Training For Agent-agnostic Action Advising In Deep Reinforcement Learning (2023)2.26