Based on DeepMind publication, I've recreated the environment and I am trying to make the DQN find and converge to an optimal policy. The task of an agent is to learn how to sustainably collect apples (objects), with the regrowth of the apples depending on its spatial configuration (the more apples around, the higher the regrowth). So in short: the agent has to find how to collect as many apples as he can (for collecting an apple he gets a reward of +1), while simultaneously allowing them to regrow, which maximizes his reward (if he depletes the resource too quickly, he looses future reward). The grid-game is visible on the picture below, where the player is a red square, his direction grey, and apple green: As given in the publication, I've built a DQN to solve the game. However, regardless of playing with learning rate, loss, exploration rate and its decay, batch size, optimizer, replay buffer, increasing the NN size the DQN does not find an optimal policy pictured below: I wonder if there is some mistake in my DQN code (with the similar implementation I've managed to solve OpenAI Gym CartPole task.) Pasting my code below:
class DDQNAgent(RLDebugger): def __init__(self, observation_space, action_space): RLDebugger.__init__(self) # get size of state and action self.state_size = observation_space self.action_size = action_space # hyper parameters self.learning_rate = .00025 self.model = self.build_model() self.target_model = self.model self.gamma = 0.999 self.epsilon_max = 1. self.epsilon = 1. self.t = 0 self.epsilon_min = 0.1 self.n_first_exploration_steps = 1500 self.epsilon_decay_len = 1000000 self.batch_size = 32 self.train_start = 64 # create replay memory using deque self.memory = deque(maxlen=1000000) self.target_model = self.build_model(trainable=False) # approximate Q function using Neural Network # state is input and Q Value of each action is output of network def build_model(self, trainable=True): model = Sequential() # This is a simple one hidden layer model, thought it should be enough here, # it is much easier to train with different achitectures (stack layers, change activation) model.add(Dense(32, input_dim=self.state_size, activation='relu', trainable=trainable)) model.add(Dense(32, activation='relu', trainable=trainable)) model.add(Dense(self.action_size, activation='linear', trainable=trainable)) model.compile(loss='mse', optimizer=RMSprop(lr=self.learning_rate)) model.summary() # 1/ You can try different losses. As an logcosh loss is a twice differenciable approximation of Huber loss # 2/ From a theoretical perspective Learning rate should decay with time to guarantee convergence return model # get action from model using greedy policy def get_action(self, state): if random.random() < self.epsilon: return random.randrange(self.action_size) q_value = self.model.predict(state) return np.argmax(q_value) # decay epsilon def update_epsilon(self): self.t += 1 self.epsilon = self.epsilon_min + max(0., (self.epsilon_max - self.epsilon_min) * (self.epsilon_decay_len - max(0., self.t - self.n_first_exploration_steps)) / self.epsilon_decay_len) # train the target network on the selected action and transition def train_model(self, action, state, next_state, reward, done): # save sample <s,a,r,s'> to the replay memory self.memory.append((state, action, reward, next_state, done)) if len(self.memory) >= self.train_start: states, actions, rewards, next_states, dones = self.create_minibatch() targets = self.model.predict(states) target_values = self.target_model.predict(next_states) for i in range(self.batch_size): # Approx Q Learning if dones[i]: targets[i][actions[i]] = rewards[i] else: targets[i][actions[i]] = rewards[i] + self.gamma * (np.amax(target_values[i])) # and do the model fit! loss = self.model.fit(states, targets, verbose=0).history['loss'] for i in range(self.batch_size): self.record(actions[i], states[i], targets[i], target_values[i], loss / self.batch_size, rewards[i]) def create_minibatch(self): # pick samples randomly from replay memory (using batch_size) batch_size = min(self.batch_size, len(self.memory)) samples = random.sample(self.memory, batch_size) states = np.array([_ for _ in samples]) actions = np.array([_ for _ in samples]) rewards = np.array([_ for _ in samples]) next_states = np.array([_ for _ in samples]) dones = np.array([_ for _ in samples]) return (states, actions, rewards, next_states, dones) def update_target_model(self): self.target_model.set_weights(self.model.get_weights())
And this is the code which I use to train the model:
from dqn_agent import * from environment import * env = GameEnv() observation_space = env.reset() agent = DDQNAgent(observation_space.shape, 7) state_size = observation_space.shape last_rewards =  episode = 0 max_episode_len = 1000 while episode < 2100: episode += 1 state = env.reset() state = np.reshape(state, [1, state_size]) #if episode % 100 == 0: # env.render_env() total_reward = 0 step = 0 gameover = False while not gameover: step += 1 #if episode % 100 == 0: # env.render_env() action = agent.get_action(state) reward, next_state, done = env.step(action) next_state = np.reshape(next_state, [1, state_size]) total_reward += reward agent.train_model(action, state, next_state, reward, done) agent.update_epsilon() state = next_state terminal = (step >= max_episode_len) if done or terminal: last_rewards.append(total_reward) agent.update_target_model() gameover = True print('episode:', episode, 'cumulative reward: ', total_reward, 'epsilon:', agent.epsilon, 'step', step)
With the model being updated after each episode (episode=1000 steps).
Looking at logs, the agent sometimes tends to achieve very high results more than few times in a row, but always fails to stabilize and the results from episode to episode have an extremely high variance (even after increasing epsilon and running for few thousands of episodes). Looking at my code and the game, do you have any ideas for what might help the algorithm stabilize the results/converge? I've been playing a lot with hyperparameters but nothing gives very significant improvement.
Some parameters on the game & training: Reward: +1 for collecting each apple (green square) Episode: 1000 steps, after 1000 steps or in case the player completely depletes the resource, the game automatically resets. Target model update: after each game termination Hyperparameters can be found in the code above.
Let me know if you have any ideas, happy to share the github repo. Feel free to email me at [email protected]
P.S. I know that this is a similar problem to the one presented below. But I have tried what has been suggested there with no success, hence decided to create another question. DQN cannot learn or converge
EDIT: Added the reward graph (below).