Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft
Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minecraft minigame ObtainDiamond with only 8M frames of environment interaction. We propose a training procedure where policy networks are first trained on human data and later fine-tuned by reinforcement learning. Using a policy exploitation mechanism, experience replay and an additional loss against catastrophic forgetting, our best agent was able to achieve a mean score of 48. Our proposed solution placed 3rd in the NeurIPS MineRL Competition for Sample-Efficient Reinforcement Learning.
Code (3)
Tasks
Deep Reinforcement LearningMinecraftreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MineRL: A Large-Scale Dataset of Minecraft Demonstrations
The sample inefficiency of standard deep reinforcement learning methods precludes their application to many real-world problems. Methods which leverage human demonstrations require fewer samples but have been researched …
BenchmarkingDeep Reinforcement LearningDiversityMinecraft+3Using Enhanced Gaussian Cross-Entropy in Imitation Learning to Digging the First Diamond in Minecraft
Although state-ofthe-art reinforcement learning (RL) systems has led to breakthroughs in many difficult tasks, the sample inefficiency of standard reinforcement learning methods still precludes their application to more …
Imitation LearningMinecraftreinforcement-learningReinforcement Learning+1DIP-RL: Demonstration-Inferred Preference Learning in Minecraft
In machine learning for sequential decision-making, an algorithmic agent learns to interact with an environment while receiving feedback in the form of a reward signal. However, in many unstructured real-world settings, …
Decision MakingMinecraftreinforcement-learningReinforcement Learning+2Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks
We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inef…
MinecraftMulti-Task Learningreinforcement-learningReinforcement Learning (RL)Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations
Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computational costs and require an incredible numbe…
Deep Reinforcement LearningHierarchical Reinforcement LearningMinecraftreinforcement-learning+2