paper-with-me

Papers

Memory Augmented Self-Play

2018-05-28 · Shagun Sodhani, Vardaan Pahuja

Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the self-play setting by providing an external memory where the agent can store experience from the previous tasks. This enables the agent to come up with more diverse self-play tasks resulting in faster exploration of the environment. The agent pretrained in the memory augmented self-play setting easily outperforms the agent pretrained in no-memory self-play setting.

📄 PDF Abstract BibTeX arXiv:1805.11016

Code (1)

shagunsodhani/memory-augmented-self-play 공식 구현 pytorch

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

2026-03-09 · Yunfei Xie, Kevin Wang, Bobby Cheng, Jianzhu Yao 외 arxiv

Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biase…

R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training

2026-02-13 · Gengsheng Li, Jinghan He, Shijie Wang, Dan Zhang 외 arxiv

Self-play bootstraps LLM reasoning through an iterative Challenger-Solver loop: the Challenger is trained to generate questions that target the Solver's capabilities, and the Solver is optimized on the generated data to …

MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution

2026-03-19 · Minhua Lin, Zhiwei Zhang, Hanqing Lu, Hui Liu 외 arxiv

Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled c…

Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory

2023-05-03 · Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu 외

With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks. Since better memory would typically prompt better generation~(w…

Abstractive Text SummarizationDialogue GenerationMachine TranslationRetrieval+3

Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory

2023-09-21 · NeurIPS 2023 11

With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks. Since better memory would typically prompt better generation (w…