paper-with-me

홈 › Papers

ETHER: Aligning Emergent Communication for Hindsight Experience Replay

2023-07-28 · Kevin Denamganaï, Daniel Hernandez, Ozan Vardal, Sondess Missaoui, James Alfred Walker

Natural language instruction following is paramount to enable collaboration between artificial agents and human beings. Natural language-conditioned reinforcement learning (RL) agents have shown how natural languages' properties, such as compositionality, can provide a strong inductive bias to learn complex policies. Previous architectures like HIGhER combine the benefit of language-conditioning with Hindsight Experience Replay (HER) to deal with sparse rewards environments. Yet, like HER, HIGhER relies on an oracle predicate function to provide a feedback signal highlighting which linguistic description is valid for which state. This reliance on an oracle limits its application. Additionally, HIGhER only leverages the linguistic information contained in successful RL trajectories, thus hurting its final performance and data-efficiency. Without early successful trajectories, HIGhER is no better than DQN upon which it is built. In this paper, we propose the Emergent Textual Hindsight Experience Replay (ETHER) agent, which builds on HIGhER and addresses both of its limitations by means of (i) a discriminative visual referential game, commonly studied in the subfield of Emergent Communication (EC), used here as an unsupervised auxiliary task and (ii) a semantic grounding scheme to align the emergent language with the natural language of the instruction-following benchmark. We show that the referential game's agents make an artificial language emerge that is aligned with the natural-like language used to describe goals in the BabyAI benchmark and that it is expressive enough so as to also describe unsuccessful RL trajectories and thus provide feedback to the RL agent to leverage the linguistic, structured information contained in all trajectories. Our work shows that EC is a viable unsupervised auxiliary task for RL and provides missing pieces to make HER more widely applicable.

📄 PDF Abstract BibTeX arXiv:2307.15494

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive BiasInstruction FollowingReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Hindsight Experience Replay

2017-07-05 · NeurIPS 2017 12 · Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider 외

Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are s…

Reinforcement LearningReinforcement Learning (RL)

Emergent Agentic Transformer from Chain of Hindsight Experience

2023-05-26 · Hao liu, Pieter Abbeel

Large transformer models powered by diverse data and model scale have dominated natural language modeling and computer vision and pushed the frontier of multiple AI areas. In reinforcement learning (RL), despite many eff…

D4RLImitation LearningLanguage ModelingLanguage Modelling+1

Hindsight Curriculum Generation Based Multi-Goal Experience Replay

2021-01-01 · Xiaoyun Feng

In multi-goal tasks with sparse rewards, it is challenging to learn from tons of experiences with zero rewards. Hindsight experience replay (HER), which replays past experiences with additional heuristic goals, has shown…

Reinforcement Learning (RL)

GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning

2025-08-08 · Xing Lei, Wenyan Yang, Kaiqiang Ke, Shentao Yang 외 arxiv

Goal-conditioned reinforcement learning (GCRL) with sparse rewards remains a fundamental challenge in reinforcement learning. While hindsight experience replay (HER) has shown promise by relabeling collected trajectories…

Reinforcement Learning

Adaptive Dialog Policy Learning with Hindsight and User Modeling

2020-05-07 · SIGDIAL (ACL) 2020 7 · Yan Cao, Keting Lu, Xiaoping Chen, Shiqi Zhang

Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences. Efficiency is of particular importance in dialog policy learning, because of the considerable cost of …

Reinforcement Learning (RL)