Quentin Gallouédec
Initial commit
22b86a8
raw
history blame
329 Bytes
!!python/object/apply:collections.OrderedDict
- - - alive_bonus_offset
- 0
- - delta_std
- 0.03
- - learning_rate
- 0.02
- - n_delta
- 32
- - n_envs
- 1
- - n_timesteps
- 12500000.0
- - n_top
- 4
- - normalize
- dict(norm_obs=True, norm_reward=False)
- - policy
- LinearPolicy