Returns the environment reward.
(self, pipeline_state: base.State)
| 55 | return jp.concatenate((position, velocity)) |
| 56 | |
| 57 | def _get_reward(self, pipeline_state: base.State) -> jax.Array: |
| 58 | """Returns the environment reward.""" |
| 59 | return ( |
| 60 | pipeline_state.x.pos[0, 0] + |
| 61 | # pipeline_state.x.pos[1, 0] + |
| 62 | # pipeline_state.x.pos[2, 0] + |
| 63 | # pipeline_state.x.pos[3, 0] + |
| 64 | - jp.clip(jp.abs(pipeline_state.x.pos[0, 2] - 1.0), -1.0, 1.0) * 0.5 |
| 65 | ) |