Customisable Unified Physical Simulations (CUPS) for Reinforcement Learning. Experiments run on the ai2thor environment (http://ai2thor.allenai.org/) e.g. using A3C, RainbowDQN and A3C_GA (Gated Attention multi-modal fusion) for Task-Oriented Language Grounding (tasks specified by natural language instructions) e.g. "Pick up the Cup or else"
agent wrapper natural-language-processing reinforcement-learning robotics simulation cup rainbow pytorch a3c transfer-learning cups multi-task-learning model-based model-free simulated-environments natural-language-instructions ai2thor-environment openai-gym-interface
-
Updated
Mar 9, 2020 - Python