README.md

metadata

tags:
  - BipedalWalker-v3
  - ars
  - deep-reinforcement-learning
  - reinforcement-learning
  - custom-implementation
  - BipedalWalkerHardcore-v3
model-index:
  - name: ARS
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: BipedalWalker-v3
          type: BipedalWalker-v3
        metrics:
          - type: mean_reward
            value: '-95.04 +/- 21.58'
            name: mean_reward
            verified: false

ARS Agent Playing BipedalWalker-v3

This is a trained model of a ARS agent playing BipedalWalker-v3.

Hyperparameters

{'v': 0.03
'N': 16
'b': 8
'lr': 0.02
'normalizer': <__main__.Normalizer object at 0x00000282A0091120>
'writer': <torch.utils.tensorboard.writer.SummaryWriter object at 0x00000282A0091750>
'env_id': 'BipedalWalker-v3'
'algorithm': 'ARS'
'iterations': 30
'episode_length': 5000
'test_iterations': 100}