tensortrade.agents.replay_memory module¶

class tensortrade.agents.replay_memory.ReplayMemory(capacity, transition_type=<class 'tensortrade.agents.replay_memory.Transition'>)[source]¶

Bases: object

head(batch_size)[source]¶

Return type:	`List`[`namedtuple`]

push(*args)[source]¶

sample(batch_size)[source]¶

Return type:	`List`[`namedtuple`]

tail(batch_size)[source]¶

Return type:	`List`[`namedtuple`]

class tensortrade.agents.replay_memory.Transition(state, action, reward, done)¶

Bases: tuple

action¶: Alias for field number 1

done¶: Alias for field number 3

reward¶: Alias for field number 2

state¶: Alias for field number 0