def make_robotics_env(env_id, seed, rank=0): """ Create a wrapped, monitored gym.Env for MuJoCo. """ set_global_seeds(seed) env = gym.make(env_id) env = FlattenObservation( FilterObservation(env, ['observation', 'desired_goal'])) env = Monitor(env, logger.get_dir() and os.path.join(logger.get_dir(), str(rank)), info_keywords=('is_success', )) env.seed(seed) return env
def make_mujoco_env(env_id, seed, reward_scale=1.0): """ Create a wrapped, monitored gym.Env for MuJoCo. """ rank = MPI.COMM_WORLD.Get_rank() myseed = seed + 1000 * rank if seed is not None else None set_global_seeds(myseed) env = gym.make(env_id) logger_path = None if logger.get_dir() is None else os.path.join( logger.get_dir(), str(rank)) env = Monitor(env, logger_path, allow_early_resets=True) env.seed(seed) if reward_scale != 1.0: from baselines_merl.common.retro_wrappers import RewardScaler env = RewardScaler(env, reward_scale) return env
def make_vec_env(env_id, env_type, num_env, seed, wrapper_kwargs=None, start_index=0, reward_scale=1.0, flatten_dict_observations=True, gamestate=None): """ Create a wrapped, monitored SubprocVecEnv for Atari and MuJoCo. """ wrapper_kwargs = wrapper_kwargs or {} mpi_rank = MPI.COMM_WORLD.Get_rank() if MPI else 0 seed = seed + 10000 * mpi_rank if seed is not None else None logger_dir = logger.get_dir() def make_thunk(rank): return lambda: make_env(env_id=env_id, env_type=env_type, mpi_rank=mpi_rank, subrank=rank, seed=seed, reward_scale=reward_scale, gamestate=gamestate, flatten_dict_observations= flatten_dict_observations, wrapper_kwargs=wrapper_kwargs, logger_dir=logger_dir) set_global_seeds(seed) if num_env > 1: return SubprocVecEnv( [make_thunk(i + start_index) for i in range(num_env)]) else: return DummyVecEnv([make_thunk(start_index)])
def learn( network, env, seed=None, total_timesteps=None, nb_epochs=None, # with default settings, perform 1M steps total nb_epoch_cycles=20, nb_rollout_steps=100, reward_scale=1.0, render=False, render_eval=False, noise_type='adaptive-param_0.2', normalize_returns=False, normalize_observations=True, critic_l2_reg=1e-2, actor_lr=1e-4, critic_lr=1e-3, popart=False, gamma=0.99, clip_norm=None, nb_train_steps=50, # per epoch cycle and MPI worker, nb_eval_steps=100, batch_size=64, # per MPI worker tau=0.01, eval_env=None, param_noise_adaption_interval=50, **network_kwargs): set_global_seeds(seed) if total_timesteps is not None: assert nb_epochs is None nb_epochs = int(total_timesteps) // (nb_epoch_cycles * nb_rollout_steps) else: nb_epochs = 500 if MPI is not None: rank = MPI.COMM_WORLD.Get_rank() else: rank = 0 nb_actions = env.action_space.shape[-1] assert (np.abs(env.action_space.low) == env.action_space.high ).all() # we assume symmetric actions. memory = Memory(limit=int(1e6), action_shape=env.action_space.shape, observation_shape=env.observation_space.shape) critic = Critic(network=network, **network_kwargs) actor = Actor(nb_actions, network=network, **network_kwargs) action_noise = None param_noise = None if noise_type is not None: for current_noise_type in noise_type.split(','): current_noise_type = current_noise_type.strip() if current_noise_type == 'none': pass elif 'adaptive-param' in current_noise_type: _, stddev = current_noise_type.split('_') param_noise = AdaptiveParamNoiseSpec( initial_stddev=float(stddev), desired_action_stddev=float(stddev)) elif 'normal' in current_noise_type: _, stddev = current_noise_type.split('_') action_noise = NormalActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions)) elif 'ou' in current_noise_type: _, stddev = current_noise_type.split('_') action_noise = OrnsteinUhlenbeckActionNoise( mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions)) else: raise RuntimeError( 'unknown noise type "{}"'.format(current_noise_type)) max_action = env.action_space.high logger.info( 'scaling actions by {} before executing in env'.format(max_action)) agent = DDPG(actor, critic, memory, env.observation_space.shape, env.action_space.shape, gamma=gamma, tau=tau, normalize_returns=normalize_returns, normalize_observations=normalize_observations, batch_size=batch_size, action_noise=action_noise, param_noise=param_noise, critic_l2_reg=critic_l2_reg, actor_lr=actor_lr, critic_lr=critic_lr, enable_popart=popart, clip_norm=clip_norm, reward_scale=reward_scale) logger.info('Using agent with the following configuration:') logger.info(str(agent.__dict__.items())) eval_episode_rewards_history = deque(maxlen=100) episode_rewards_history = deque(maxlen=100) sess = U.get_session() # Prepare everything. agent.initialize(sess) sess.graph.finalize() agent.reset() obs = env.reset() if eval_env is not None: eval_obs = eval_env.reset() nenvs = obs.shape[0] episode_reward = np.zeros(nenvs, dtype=np.float32) #vector episode_step = np.zeros(nenvs, dtype=int) # vector episodes = 0 #scalar t = 0 # scalar epoch = 0 start_time = time.time() epoch_episode_rewards = [] epoch_episode_steps = [] epoch_actions = [] epoch_qs = [] epoch_episodes = 0 for epoch in range(nb_epochs): for cycle in range(nb_epoch_cycles): # Perform rollouts. if nenvs > 1: # if simulating multiple envs in parallel, impossible to reset agent at the end of the episode in each # of the environments, so resetting here instead agent.reset() for t_rollout in range(nb_rollout_steps): # Predict next action. action, q, _, _ = agent.step(obs, apply_noise=True, compute_Q=True) # Execute next action. if rank == 0 and render: env.render() # max_action is of dimension A, whereas action is dimension (nenvs, A) - the multiplication gets broadcasted to the batch new_obs, r, done, info = env.step( max_action * action ) # scale for execution in env (as far as DDPG is concerned, every action is in [-1, 1]) # note these outputs are batched from vecenv t += 1 if rank == 0 and render: env.render() episode_reward += r episode_step += 1 # Book-keeping. epoch_actions.append(action) epoch_qs.append(q) agent.store_transition( obs, action, r, new_obs, done ) #the batched data will be unrolled in memory.py's append. obs = new_obs for d in range(len(done)): if done[d]: # Episode done. epoch_episode_rewards.append(episode_reward[d]) episode_rewards_history.append(episode_reward[d]) epoch_episode_steps.append(episode_step[d]) episode_reward[d] = 0. episode_step[d] = 0 epoch_episodes += 1 episodes += 1 if nenvs == 1: agent.reset() # Train. epoch_actor_losses = [] epoch_critic_losses = [] epoch_adaptive_distances = [] for t_train in range(nb_train_steps): # Adapt param noise, if necessary. if memory.nb_entries >= batch_size and t_train % param_noise_adaption_interval == 0: distance = agent.adapt_param_noise() epoch_adaptive_distances.append(distance) cl, al = agent.train() epoch_critic_losses.append(cl) epoch_actor_losses.append(al) agent.update_target_net() # Evaluate. eval_episode_rewards = [] eval_qs = [] if eval_env is not None: nenvs_eval = eval_obs.shape[0] eval_episode_reward = np.zeros(nenvs_eval, dtype=np.float32) for t_rollout in range(nb_eval_steps): eval_action, eval_q, _, _ = agent.step(eval_obs, apply_noise=False, compute_Q=True) eval_obs, eval_r, eval_done, eval_info = eval_env.step( max_action * eval_action ) # scale for execution in env (as far as DDPG is concerned, every action is in [-1, 1]) if render_eval: eval_env.render() eval_episode_reward += eval_r eval_qs.append(eval_q) for d in range(len(eval_done)): if eval_done[d]: eval_episode_rewards.append(eval_episode_reward[d]) eval_episode_rewards_history.append( eval_episode_reward[d]) eval_episode_reward[d] = 0.0 if MPI is not None: mpi_size = MPI.COMM_WORLD.Get_size() else: mpi_size = 1 # Log stats. # XXX shouldn't call np.mean on variable length lists duration = time.time() - start_time stats = agent.get_stats() combined_stats = stats.copy() combined_stats['rollout/return'] = np.mean(epoch_episode_rewards) combined_stats['rollout/return_std'] = np.std(epoch_episode_rewards) combined_stats['rollout/return_history'] = np.mean( episode_rewards_history) combined_stats['rollout/return_history_std'] = np.std( episode_rewards_history) combined_stats['rollout/episode_steps'] = np.mean(epoch_episode_steps) combined_stats['rollout/actions_mean'] = np.mean(epoch_actions) combined_stats['rollout/Q_mean'] = np.mean(epoch_qs) combined_stats['train/loss_actor'] = np.mean(epoch_actor_losses) combined_stats['train/loss_critic'] = np.mean(epoch_critic_losses) combined_stats['train/param_noise_distance'] = np.mean( epoch_adaptive_distances) combined_stats['total/duration'] = duration combined_stats['total/steps_per_second'] = float(t) / float(duration) combined_stats['total/episodes'] = episodes combined_stats['rollout/episodes'] = epoch_episodes combined_stats['rollout/actions_std'] = np.std(epoch_actions) # Evaluation statistics. if eval_env is not None: combined_stats['eval/return'] = eval_episode_rewards combined_stats['eval/return_history'] = np.mean( eval_episode_rewards_history) combined_stats['eval/Q'] = eval_qs combined_stats['eval/episodes'] = len(eval_episode_rewards) def as_scalar(x): if isinstance(x, np.ndarray): assert x.size == 1 return x[0] elif np.isscalar(x): return x else: raise ValueError('expected scalar, got %s' % x) combined_stats_sums = np.array( [np.array(x).flatten()[0] for x in combined_stats.values()]) if MPI is not None: combined_stats_sums = MPI.COMM_WORLD.allreduce(combined_stats_sums) combined_stats = { k: v / mpi_size for (k, v) in zip(combined_stats.keys(), combined_stats_sums) } # Total statistics. combined_stats['total/epochs'] = epoch + 1 combined_stats['total/steps'] = t for key in sorted(combined_stats.keys()): logger.record_tabular(key, combined_stats[key]) if rank == 0: logger.dump_tabular() logger.info('') logdir = logger.get_dir() if rank == 0 and logdir: if hasattr(env, 'get_state'): with open(os.path.join(logdir, 'env_state.pkl'), 'wb') as f: pickle.dump(env.get_state(), f) if eval_env and hasattr(eval_env, 'get_state'): with open(os.path.join(logdir, 'eval_env_state.pkl'), 'wb') as f: pickle.dump(eval_env.get_state(), f) return agent
def learn(*, network, env, total_timesteps, eval_env=None, seed=None, nsteps=2048, ent_coef=0.0, lr=3e-4, vf_coef=0.5, ve_coef=0.5, fs_coef=0.01, nfs=1, max_grad_norm=0.5, gamma=0.99, lam=0.95, log_interval=10, nminibatches=4, noptepochs=4, cliprange=0.2, save_interval=0, load_path=None, model_fn=None, **network_kwargs): ''' Learn policy using PPO algorithm (https://arxiv.org/abs/1707.06347) Parameters: ---------- network: policy network architecture. Either string (mlp, lstm, lnlstm, cnn_lstm, cnn, cnn_small, conv_only - see baselines_merl.common/models.py for full list) specifying the standard network architecture, or a function that takes tensorflow tensor as input and returns tuple (output_tensor, extra_feed) where output tensor is the last network layer output, extra_feed is None for feed-forward neural nets, and extra_feed is a dictionary describing how to feed state into the network for recurrent neural nets. See common/models.py/lstm for more details on using recurrent nets in policies env: baselines_merl.common.vec_env.VecEnv environment. Needs to be vectorized for parallel environment simulation. The environments produced by gym.make can be wrapped using baselines_merl.common.vec_env.DummyVecEnv class. nsteps: int number of steps of the vectorized environment per update (i.e. batch size is nsteps * nenv where nenv is number of environment copies simulated in parallel) total_timesteps: int number of timesteps (i.e. number of actions taken in the environment) ent_coef: float policy entropy coefficient in the optimization objective lr: float or function learning rate, constant or a schedule function [0,1] -> R+ where 1 is beginning of the training and 0 is the end of the training. vf_coef: float value function loss coefficient in the optimization objective max_grad_norm: float or None gradient norm clipping coefficient gamma: float discounting factor lam: float advantage estimation discounting factor (lambda in the paper) log_interval: int number of timesteps between logging events nminibatches: int number of training minibatches per update. For recurrent policies, should be smaller or equal than number of environments run in parallel. noptepochs: int number of training epochs per update cliprange: float or function clipping range, constant or schedule function [0,1] -> R+ where 1 is beginning of the training and 0 is the end of the training save_interval: int number of timesteps between saving events load_path: str path to load the model from **network_kwargs: keyword arguments to the policy / network builder. See baselines_merl.common/policies_baseline.py/build_policy and arguments to a particular type of network For instance, 'mlp' network architecture has arguments num_hidden and num_layers. ''' set_global_seeds(seed) if isinstance(lr, float): lr = constfn(lr) else: assert callable(lr) if isinstance(cliprange, float): cliprange = constfn(cliprange) else: assert callable(cliprange) total_timesteps = int(total_timesteps) policy = build_policy(env, network, **network_kwargs) # Get the nb of env nenvs = env.num_envs # Get state_space and action_space ob_space = env.observation_space ac_space = env.action_space # Calculate the batch_size nbatch = nenvs * nsteps nbatch_train = nbatch // nminibatches # Instantiate the model object (that creates act_model and train_model) if model_fn is None: from baselines_merl.ppo2_merl.model import Model model_fn = Model model = model_fn(policy=policy, ob_space=ob_space, ac_space=ac_space, nbatch_act=nenvs, nbatch_train=nbatch_train, nsteps=nsteps, ent_coef=ent_coef, vf_coef=vf_coef, ve_coef=ve_coef, fs_coef=fs_coef, nfs=nfs, max_grad_norm=max_grad_norm) if load_path is not None: model.load(load_path) # Instantiate the runner object runner = Runner(env=env, model=model, nsteps=nsteps, gamma=gamma, lam=lam) if eval_env is not None: eval_runner = Runner(env=eval_env, model=model, nsteps=nsteps, gamma=gamma, lam=lam) epinfobuf = deque(maxlen=100) if eval_env is not None: eval_epinfobuf = deque(maxlen=100) # Start total timer tfirststart = time.time() nupdates = total_timesteps // nbatch for update in range(1, nupdates + 1): assert nbatch % nminibatches == 0 # Start timer tstart = time.time() frac = 1.0 - (update - 1.0) / nupdates # Calculate the learning rate lrnow = lr(frac) # Calculate the cliprange cliprangenow = cliprange(frac) # Get minibatch obs, returns, masks, actions, values, neglogpacs, states, epinfos, count = runner.run( ) #pylint: disable=E0632 if eval_env is not None: eval_obs, eval_returns, eval_masks, eval_actions, eval_values, eval_neglogpacs, eval_states, eval_epinfos, count = eval_runner.run( ) #pylint: disable=E0632 epinfobuf.extend(epinfos) if eval_env is not None: eval_epinfobuf.extend(eval_epinfos) # Here what we're going to do is for each minibatch calculate the loss and append it. mblossvals = [] if states is None: # nonrecurrent version # Index of each element of batch_size # Create the indices array inds = np.arange(nbatch) for _ in range(noptepochs): # Randomize the indexes np.random.shuffle(inds) # 0 to batch_size with batch_train_size step for start in range(0, nbatch, nbatch_train): end = start + nbatch_train mbinds = inds[start:end] slices = (arr[mbinds] for arr in (obs, returns, masks, actions, values, neglogpacs)) mblossvals.append( model.train(lrnow, count, cliprangenow, *slices)) else: # recurrent version assert nenvs % nminibatches == 0 envsperbatch = nenvs // nminibatches envinds = np.arange(nenvs) flatinds = np.arange(nenvs * nsteps).reshape(nenvs, nsteps) envsperbatch = nbatch_train // nsteps for _ in range(noptepochs): np.random.shuffle(envinds) for start in range(0, nenvs, envsperbatch): end = start + envsperbatch mbenvinds = envinds[start:end] mbflatinds = flatinds[mbenvinds].ravel() slices = (arr[mbflatinds] for arr in (obs, returns, masks, actions, values, neglogpacs)) mbstates = states[mbenvinds] mblossvals.append( model.train(lrnow, count, cliprangenow, *slices, mbstates)) # Feedforward --> get losses --> update lossvals = np.mean(mblossvals, axis=0) # End timer tnow = time.time() # Calculate the fps (frame per second) fps = int(nbatch / (tnow - tstart)) if update % log_interval == 0 or update == 1: # Calculates if value function is a good predicator of the returns (ev > 1) # or if it's just worse than predicting nothing (ev =< 0) ev = explained_variance(values, returns) logger.logkv("serial_timesteps", update * nsteps) logger.logkv("nupdates", update) logger.logkv("total_timesteps", update * nbatch) logger.logkv("fps", fps) logger.logkv("explained_variance", float(ev)) logger.logkv('eprewmean', safemean([epinfo['r'] for epinfo in epinfobuf])) logger.logkv('eplenmean', safemean([epinfo['l'] for epinfo in epinfobuf])) if eval_env is not None: logger.logkv( 'eval_eprewmean', safemean([epinfo['r'] for epinfo in eval_epinfobuf])) logger.logkv( 'eval_eplenmean', safemean([epinfo['l'] for epinfo in eval_epinfobuf])) logger.logkv('time_elapsed', tnow - tfirststart) for (lossval, lossname) in zip(lossvals, model.loss_names): logger.logkv(lossname, lossval) if MPI is None or MPI.COMM_WORLD.Get_rank() == 0: logger.dumpkvs() if save_interval and (update % save_interval == 0 or update == 1) and logger.get_dir() and ( MPI is None or MPI.COMM_WORLD.Get_rank() == 0): checkdir = osp.join(logger.get_dir(), 'checkpoints') os.makedirs(checkdir, exist_ok=True) savepath = osp.join(checkdir, '%.5i' % update) print('Saving to', savepath) model.save(savepath) return model