Deep-Reinforcement-Learning-Minigrid
PublicDeep RL agents for the MiniGrid 6 Rooms. Implements DQN, Double DQN, Huber Loss, Soft Updates, PER, and Actor-Critic. Best model solves 90% of episodes with improved training stability.
Deep RL agents for the MiniGrid 6 Rooms. Implements DQN, Double DQN, Huber Loss, Soft Updates, PER, and Actor-Critic. Best model solves 90% of episodes with improved training stability.