File size: 2,242 Bytes
e085e3b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
from tqdm import trange
def fill_memory(agent, env, num_episodes=500 ):
print("Filling up memory....")
for _ in trange(500):
state = env.reset()
done = False
while not done:
action = agent.act(state)
next_state, reward, done, _ = env.step(action)
agent.cache(state, next_state, action, reward, done)
state = next_state
# def train(agent, env, logger):
# episodes = 5000
# for e in range(episodes):
# state = env.reset()
# # Play the game!
# while True:
# # Run agent on the state
# action = agent.act(state)
# # Agent performs action
# next_state, reward, done, info = env.step(action)
# # Remember
# agent.cache(state, next_state, action, reward, done)
# # Learn
# q, loss = agent.learn()
# # Logging
# logger.log_step(reward, loss, q)
# # Update state
# state = next_state
# # Check if end of game
# if done:
# break
# logger.log_episode(e)
# if e % 20 == 0:
# logger.record(episode=e, epsilon=agent.exploration_rate, step=agent.curr_step)
def train(agent, env, logger):
episodes = 5000
for e in range(episodes):
state = env.reset()
# Play the game!
for i in range(1000):
# Run agent on the state
action = agent.act(state)
env.render()
# Agent performs action
next_state, reward, done, info = env.step(action)
# Remember
agent.cache(state, next_state, action, reward, done, i)
# Learn
q, loss = agent.learn()
# Logging
logger.log_step(reward, loss, q)
# Update state
state = next_state
# Check if end of game
if done:
break
logger.log_episode(e)
if e % 20 == 0:
logger.record(episode=e, epsilon=agent.exploration_rate, step=agent.curr_step)
|