pythonlessons
problem with train_agent and self.get_gaes
deltas = [r + gamma * (1 - d) * nv - v for r, d, nv, v in zip(rewards, dones, next_values, values)]
TypeError: unsupported operand type(s) for +: 'NoneType' and 'float'
rewards = [0 if reward is None else reward for reward in rewards]
Add this above deltas = [r + ....
deltas = [r + gamma * (1 - d) * nv - v for r, d, nv, v in zip(rewards, dones, next_values, values)]
TypeError: unsupported operand type(s) for +: 'NoneType' and 'float'
Where you able to solve this?
rewards = [0 if reward is None else reward for reward in rewards]
Add this above deltas = [r + ....
Mind elaborating a bit more? It didnt solved the issue at my end, any help is highly appreciated. Thanks!