llm使用 AgentScope-Tuner 通过 RL 训练 FrozenLake 智能体
agentscope-samples/tuner/frozen_lake at main · agentscope-ai/agentscope-samples --- agentscope-samples/tuner/frozen_lake at main · agentscope-ai/agentscope-samplesAt least 2 NVIDIA GPUs with CUDA 12.8 or newer至少需要 2 块 NVIDIA GPU支持 CUDA 12.8 或更高版本An example of agent output is given below:下面给出一个代理输出的示例From the current observation, lets analyze the situation. The player (P) is at: (4, 0), and the goal (G) is at: (2, 3). There is also a hole (O) at (4, 4). Given this, I can move towards the goal without worrying about slippery tiles right now. The shortest path from P to G involves moving left (4 steps) followed by moving down (1 step), since going directly would bypass the hole or move us further from the goal. Lets move left first. Lets take the action Left.
)
)
