Zhong, V;
Rocktäschel, T;
Grefenstette, E;
(2020)
RTFM: Generalising to New Environment Dynamics via Reading.
In:
Proceedings of the International Conference on Learning Representations (ICLR 2020).
(pp. pp. 1-17).
ICLR
Preview |
Text
rtfm_generalising_to_new_environment_dynamics_via_reading.pdf - Published Version Download (2MB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | RTFM: Generalising to New Environment Dynamics via Reading |
| Event: | International Conference on Learning Representations (ICLR 2020) |
| Location: | Addis Ababa, Ethiopia |
| Dates: | 26th April - 1st May 2020 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://openreview.net/forum?id=SJgob6NKvH |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions. |
| Keywords: | reinforcement learning, policy learning, reading comprehension, generalisation |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10101221 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
