arXiv:1804.03720

Gotta Learn Fast: A New Benchmark for Generalization in RL

Alex Nichol, Vicki Pfau, Christopher Hesse, Oleg Klimov, John Schulman

제출 2018-04-10

원문 초록

In this report, we present a new reinforcement learning (RL) benchmark based on the Sonic the Hedgehog (TM) video game franchise. This benchmark is intended to measure the performance of transfer learning and few-shot learning algorithms in the RL domain. We also present and evaluate some baseline algorithms on the new benchmark.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2507.10990공통 태그 reinforcement-learning, Reinforcement Learning, Reinforcement Learning (RL)공식 코드 · Papers with Code 등록 2025-07-15

High-Throughput Distributed Reinforcement Learning via Adaptive Policy Synchronization

arXiv:2507.11486공통 태그 reinforcement-learning, Reinforcement Learning, Reinforcement Learning (RL)공식 코드 · Papers with Code 등록 2025-07-15

Exploring the robustness of TractOracle methods in RL-based tractography

arXiv:2507.09087공통 태그 reinforcement-learning, Reinforcement Learning, Reinforcement Learning (RL)공식 코드 · Papers with Code 등록 2025-07-12

Deep Reinforcement Learning with Gradient Eligibility Traces

arXiv:2507.05687공통 태그 reinforcement-learning, Reinforcement Learning, Reinforcement Learning (RL)공식 코드 · Papers with Code 등록 2025-07-08

AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs

arXiv:2507.03026공통 태그 Reinforcement Learning, Reinforcement Learning (RL), Transfer Learning공식 코드 · Papers with Code 등록 2025-07-02

Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains

arXiv:2506.20512공통 태그 reinforcement-learning, Reinforcement Learning, Reinforcement Learning (RL)공식 코드 · Papers with Code 등록 2025-06-25

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

토론

이 논문과 연결된 포럼 글이 아직 없습니다.

포럼에서 토론 찾기