Learning Task Informed Abstractions
Fu, Xiang, Yang, Ge, Agrawal, Pulkit, Jaakkola, Tommi
–arXiv.org Artificial Intelligence
Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features. To mitigate this problem, we propose learning Task Informed Abstractions (TIA) that explicitly separates reward-correlated visual features from distractors. For learning TIA, we introduce the formalism of Task Informed MDP (TiMDP) that is realized by training two models that learn visual features via cooperative reconstruction, but one model is adversarially dissociated from the reward signal. Empirical evaluation shows that TIA leads to significant performance gains over state-of-the-art methods on many visual control tasks where natural and unconstrained visual distractions pose a formidable challenge.
arXiv.org Artificial Intelligence
Jun-29-2021
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- Rhode Island > Providence County
- Providence (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- California > Los Angeles County
- Long Beach (0.14)
- Rhode Island > Providence County
- Canada > Quebec
- Montreal (0.04)
- United States
- Europe > Spain
- Catalonia > Barcelona Province > Barcelona (0.04)
- Asia
- China > Hong Kong (0.04)
- Middle East > Jordan (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Oceania > Australia
- Genre:
- Research Report
- New Finding (0.46)
- Promising Solution (0.34)
- Research Report
- Industry:
- Leisure & Entertainment > Games (0.47)
- Technology: