RTFM: Generalising to Novel Environment Dynamics via Reading

by   Victor Zhong, et al.

Obtaining policies that can generalise to new environments in reinforcement learning is challenging. In this work, we demonstrate that language understanding via a reading policy learner is a promising vehicle for generalisation to new environments. We propose a grounded policy learning problem, Read to Fight Monsters (RTFM), in which the agent must jointly reason over a language goal, relevant dynamics described in a document, and environment observations. We procedurally generate environment dynamics and corresponding language descriptions of the dynamics, such that agents must read to understand new environment dynamics instead of memorising any particular information. In addition, we propose txt2π, a model that captures three-way interactions between the goal, document, and observations. On RTFM, txt2π generalises to new environments with dynamics not seen during training via reading. Furthermore, our model outperforms baselines such as FiLM and language-conditioned CNNs on RTFM. Through curriculum learning, txt2π produces policies that excel on complex RTFM tasks requiring several reasoning and coreference steps.


page 3

page 11

page 15


Improving Policy Learning via Language Dynamics Distillation

Recent work has shown that augmenting environments with language descrip...

Towards Optimal Head-to-head Autonomous Racing with Curriculum Reinforcement Learning

Head-to-head autonomous racing is a challenging problem, as the vehicle ...

Nested Policy Reinforcement Learning

Off-policy reinforcement learning (RL) has proven to be a powerful frame...

MANGA: Method Agnostic Neural-policy Generalization and Adaptation

In this paper we target the problem of transferring policies across mult...

Fast Adaptation via Policy-Dynamics Value Functions

Standard RL algorithms assume fixed environment dynamics and require a s...

BabyAI++: Towards Grounded-Language Learning beyond Memorization

Despite success in many real-world tasks (e.g., robotics), reinforcement...

Interpretable Reinforcement Learning with Multilevel Subgoal Discovery

We propose a novel Reinforcement Learning model for discrete environment...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset