ppo-PandaReach-v3 / config.yml
liajun's picture
PandaReach-v3 PPO agent with 100% success rate
4753c9d verified
!!python/object/apply:collections.OrderedDict
- - - batch_size
- 512
- - clip_range
- 0.2
- - ent_coef
- 0.00066
- - gae_lambda
- 0.9978
- - gamma
- 0.99779
- - learning_rate
- 0.00044
- - max_grad_norm
- 0.77
- - n_envs
- 16
- - n_epochs
- 10
- - n_steps
- 2048
- - n_timesteps
- 1000000.0
- - normalize
- true
- - policy
- MultiInputPolicy
- - policy_kwargs
- dict( net_arch=[256, 256], activation_fn=nn.ReLU )