README.md

metadata

tags:
  - MountainCar-v0
  - deep-reinforcement-learning
  - reinforcement-learning
model-index:
  - name: DQN
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: MountainCar-v0
          type: MountainCar-v0
        metrics:
          - type: mean_reward
            value: '-120.10 +/- 19.30'
            name: mean_reward
            verified: false
license: afl-3.0

DQN Agent playing MountainCar-v0

This is a trained model of a DQN agent playing MountainCar-v0. We train a three-layer MLP as the Q-network. We store the transitions in a replay buffer. After the network converges, we stop training and validate its performance in comparison to a random baseline.

Parameters:

hidden_size = 64
gamma = 0.99
epsilon_decay = 0.999
buffer_size = 10000
batch_size = 64
episodes = 10000