We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Leveraging pre-trained language models to gen-001 erate action plans for embodied agents is an 002 emerging research direction. However, exe… (see more)-003 cuting instructions in real or simulated envi-004 ronments necessitates verifying the feasibility 005 of actions and their relevance in achieving a 006 goal. We introduce a novel method that in-007 tegrates a language model and reinforcement 008 learning for constructing objects in a Minecraft-009 like environment, based on natural language 010 instructions. Our method generates a set of 011 consistently achievable sub-goals derived from 012 the instructions and subsequently completes the 013 associated sub-tasks using a pre-trained RL pol-014 icy. We employ the IGLU competition, which 015 is based on the Minecraft-like simulator, as our 016 test environment, and compare our approach 017 to the competition’s top-performing solutions. 018 Our approach outperforms existing solutions in 019 terms of both the quality of the language model 020 and the quality of the structures built within the 021 IGLU environment. 022
Learning to Guide and to Be Guided in the Architect-Builder Problem
Adversarial imitation learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones … (see more)-- and a generator's policy to produce trajectories that can fool this discriminator. This alternated optimization is known to be delicate in practice since it compounds unstable adversarial training with brittle and sample-inefficient reinforcement learning. We propose to remove the burden of the policy optimization steps by leveraging a novel discriminator formulation. Specifically, our discriminator is explicitly conditioned on two policies: the one from the previous generator's iteration and a learnable policy. When optimized, this discriminator directly learns the optimal generator's policy. Consequently, our discriminator's update solves the generator's optimization problem for free: learning a policy that imitates the expert does not require an additional optimization loop. This formulation effectively cuts by half the implementation and computational burden of adversarial imitation learning algorithms by removing the reinforcement learning phase altogether. We show on a variety of tasks that our simpler approach is competitive to prevalent imitation learning methods.
