diff --git a/main.py b/main.py index 110afcb..10897d9 100644 --- a/main.py +++ b/main.py @@ -144,27 +144,6 @@ class TensorboardCallback(BaseCallback): return True -def sample_random_action(agent, mask): - """Sample random UNMASKED action(s) for agent.""" - # Return a list of actions: 1 for each action subspace - if agent.multi_action_mode: - split_masks = np.split(mask, agent.action_spaces.cumsum()[:-1]) - return [np.random.choice(np.arange(len(m_)), p=m_/m_.sum()) for m_ in split_masks] - - # Return a single action - else: - return np.random.choice(np.arange(agent.action_spaces), p=mask/mask.sum()) - -def sample_random_actions(env, obs): - """Samples random UNMASKED actions for each agent in obs.""" - - actions = { - a_idx: 0 - for a_idx in range( len(obs)) - } - - return actions - def printMarket(market): for i in range(len(market)): step=market[i]