HF RL Explorer

I want a stateful DQN algorithm class for discrete Gym action spaces that can be imported with from…

I want a stateful DQN algorithm class for discrete Gym action spaces that can be imported with from…: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). I want a stateful DQN algorithm class for discrete Gym action spaces that can be imported with from rljax.algorithm import…

The task

I want a stateful DQN algorithm class for discrete Gym action spaces that can be imported with from rljax.algorithm import DQN and from rljax.algorithm.dqn import DQN. Its constructor should be DQN(num_agent_steps, state_space, action_space, seed, max_grad_norm=None…

Part of XiaomiMiMo/MiMo-V2.6-RL-oss.