python cs285/scripts/run_hw4.py -cfg experiments/mpc/halfcheetah_0_iter_layer_1_size_32.yaml python cs285/scripts/run_hw4.py -cfg experiments/mpc/halfcheetah_0_iter_layer_1_size_16.yaml python cs285/scripts/run_hw4.py -cfg experiments/mpc/halfcheetah_0_iter_layer_2_size_16.yaml Get predictions pred_obs_deltas_normalized = self.dynamics_modelsi pred_obs_deltas = pred_obs_deltas_normalized * self.obs_delta_std + self.obs_delta_mean pred_next_obs = obs + pred_obs_deltas ``` Action Selection rewards = np.array([

Note: All Yaml files are in the git repo: https://github.com/jimchen2/cs285-reinforcement-learning python cs285/scripts/run_hw5_explore.py \ python cs285/scripts/run_hw5_explore.py \ python cs285/scripts/run_hw5_explore.py \ The Random Network Distillation algorithm encourages exploration by training another neural network to approximate the output

Compute Action and use epsilon greedy action = torch.tensor(random.randint(0, self.num_actions - 1)) action = self.critic(observation).argmax(dim=1) Step environment Add data to replay buffer replay_buffer.insert(...) Sample from replay buffer batch = replay_buffer.sample(config["batch_size"]) Train agent, we update the

There are 2 kinds of estimator for Policy Gradients, full trajectory and and "reward-to-go" We run the two configs on Cartpole with different parameters, specifically, rtg means reward to go, na means normalizing the advantages.

We run imitation learning and Dagger based on expert policies. In this experiment the expert policy is directly sampled out from a trained Neural Network, so Dagger differs from real world applications in that it

Downtown Berkeley is really ugly and there are many homeless people. They yell, beg for money, shout profanity, and sometimes run around nude. I could smell the scent when walking past them, like they hadn't

It has been a while since I posted, and Class is starting tomorrow. Today is Martin Luther King Day. Everybody takes a day off. Today is a fine day, the sun shining bright and clear

Today I went to BHS for a visit; I mean, I basically sneaked into the campus for a whole morning. Now I am going to talk about the impressions I had of that school. I

When I applied, I wasn't very serious; I just wanted to take a chance. I started the form on Oct 7th. At that time, I was still hesitating about whether to go to an exchange