Resets the environment to an initial state.
(self, rng: jax.Array)
| 23 | super().__init__(sys=sys, backend=backend, **kwargs) |
| 24 | |
| 25 | def reset(self, rng: jax.Array) -> State: |
| 26 | """Resets the environment to an initial state.""" |
| 27 | rng, rng1, rng2 = jax.random.split(rng, 3) |
| 28 | |
| 29 | q = self.sys.init_q + jax.random.uniform( |
| 30 | rng1, (self.sys.q_size(),), minval=-0.01, maxval=0.01 |
| 31 | ) + jp.array([0.0, jp.pi]) |
| 32 | qd = jax.random.uniform(rng2, (self.sys.qd_size(),), minval=-0.01, maxval=0.01) |
| 33 | pipeline_state = self.pipeline_init(q, qd) |
| 34 | obs = self._get_obs(pipeline_state) |
| 35 | reward, done = jp.zeros(2) |
| 36 | metrics = {} |
| 37 | |
| 38 | return State(pipeline_state, obs, reward, done, metrics) |
| 39 | |
| 40 | def step(self, state: State, action: jax.Array) -> State: |
| 41 | """Run one timestep of the environment's dynamics.""" |