garage.np.policies.scripted_policy module

Simulates a garage policy object.

class ScriptedPolicy(scripted_actions, agent_env_infos=None)

Bases: object

Simulates a garage policy object.

Parameters:

• scripted actions (-) – data structure indexed by obervation, returns a corresponding action
• agent_env_infos (-) – data structure indexed by obervation, returns a corresponding agent_env_info

get_action(obs)

Return action sampled from the policy.

get_actions(obses)

Return ACTIONS sampled from the policy.

get_param_values()

Return policy params as a list.

reset(dones=None)

Reset Policy to initial state.

set_param_values(params)

Set param values of policy.