AI Strategy and Concepts Bibliography

WIKINDX Resources

Hester, T., Vecerik, M., Pietquin, O., Lanctot, M., Schaul, T., & Piot, B., et al. 2018, Deep q-learning from demonstrations. Paper presented at Thirty-Second AAAI Conference on Artificial Intelligence. 
Added by: SijanLibrarian (2020-07-09 10:11:54)   Last edited by: SijanLibrarian (2020-07-09 10:13:08)
Resource type: Proceedings Article
BibTeX citation key: Hester2018
Email resource to friend
View all bibliographic details
Categories: Artificial Intelligence, Computer Science, Data Sciences, Decision Theory, General, Mathematics
Subcategories: AI transfer learning, Decision making, Deep learning, Machine learning, Markov models, Q-learning
Creators: Hester, Horgan, Lanctot, Osband, others, Pietquin, Piot, Quan, Schaul, Sendonaris, Vecerik
Collection: Thirty-Second AAAI Conference on Artificial Intelligence
Views: 47/61
Views index: 14%
Popularity index: 3.5%
Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor. This may be acceptable for a simulator, but it severely limits the applicability of deep RL to many real-world tasks, where the agent must learn in the real environment. In this paper we study a setting where the agent may access data from previous control of the system. We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstration data and is able to automatically assess the necessary ratio of demonstration data while learning thanks to a prioritized replay mechanism. DQfD works by combining temporal difference updates with supervised classification of the demonstrator’s actions. We show that DQfD has better initial performance than Prioritized Dueling Double Deep Q-Networks (PDD DQN) as it starts with better scores on the first million steps on 41 of 42 games and on average it takes PDD DQN 83 million steps to catch up to DQfD’s performance. DQfD learns to out-perform the best demonstration given in 14 of 42 games. In addition, DQfD leverages human demonstrations to achieve state-of-the-art results for 11 games. Finally, we show that DQfD performs better than three related algorithms for incorporating demonstration data into DQN.
wikindx 6.2.2 ©2003-2020 | Total resources: 1447 | Username: -- | Bibliography: WIKINDX Master Bibliography | Style: American Psychological Association (APA) | Database queries: 66 | DB execution: 0.11387 secs | Script execution: 0.12753 secs