数据链接:
官方服务:
资源简介:
MATLAB codes for 5-state-2-action MDPs: Relative Actor Critic
应用场景:
创建时间:
2024-09-09
相关数据集
EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning
Offline-to-online is a key strategy for advancing reinforcement learning towards practical applications. This approach not only reduces the risks and costs associated with online exploration, but also
DataCite Commons2024-10-28 更新110
Finger-Gaiting Manipulation Dataset
该数据集旨在学习使用次优控制器进行手内操作技能的指关节控制。它包含了多种方法的结果,包括标准的非策略强化学习以及行为克隆损失版本。数据集涵盖了多种物体,如立方体、球体、圆柱体、十二面体和二十面体,针对的任务是灵巧的手内操作。
arXiv90
luca0621/multi-RLHF-processed-llama1B-dataset-with-1000-rewards
该数据集包含查询(query)、响应(response)和奖励(reward)三个特征,其中查询和响应为字符串类型,奖励为浮点数类型。数据集分为训练集和测试集,训练集包含8000个样本,测试集包含2000个样本。总下载大小为2276183字节,数据集总大小为7148705字节。
Hugging Face2024-11-30 更新70
yonghoon96/antmaze-giant-navigate-20m-v0
--- license: mit task_categories: - reinforcement-learning tags: - offline-rl - goal-conditioned-rl - mujoco - antmaze size_categories: - 10M<n<100M --- # AntMaze-Giant-Navigate 20M Dataset This da
Hugging Face2026-02-21 更新100
ai2-adapt-dev/sft_v3.9_used_on_policy_p0_olmo2_7b
--- dataset_info: features: - name: prompt dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list:
Hugging Face2024-11-23 更新90



