Quentin Gallouédec
Initial commit
92e44f0
raw
history blame
367 Bytes
!!python/object/apply:collections.OrderedDict
- - - delta_std
- 0.1
- - learning_rate
- 0.018
- - n_delta
- 4
- - n_envs
- 1
- - n_timesteps
- 2000000.0
- - n_top
- 1
- - normalize
- dict(norm_obs=True, norm_reward=False)
- - policy
- MlpPolicy
- - policy_kwargs
- dict(net_arch=[16])
- - zero_policy
- false