'replay_buffer': replay_buffer,
'num_iters': num_iters,
'monitor_state': monitored_env.get_state()
})
if info["steps"] > args.num_steps:
break
if done:
steps_left = args.num_steps - info["steps"]
completion = np.round(info["steps"] / args.num_steps, 1)
mean_ep_reward = np.mean(info["rewards"][-100:])
logger.record_tabular("% completion", completion)
logger.record_tabular("steps", info["steps"])
logger.record_tabular("iters", num_iters)
logger.record_tabular("episodes", len(info["rewards"]))
logger.record_tabular("reward (100 epi mean)", np.mean(info["rewards"][-100:]))
if not args.noisy:
logger.record_tabular("exploration", exploration.value(num_iters))
if args.prioritized:
logger.record_tabular("max priority", replay_buffer._max_priority)
fps_estimate = (float(steps_per_iter) / (float(iteration_time_est) + 1e-6)
if steps_per_iter._value is not None else "calculating...")
logger.dump_tabular()
logger.log()
logger.log("ETA: " + pretty_eta(int(steps_left / fps_estimate)))
logger.log()
# add summary for one episode
ep_stats.add_all_summary(writer, [mean_ep_reward, ep_length], num_iters)
ep_length = 0
if done:
steps_left = args.num_steps - info["steps"]
completion = np.round(info["steps"] / args.num_steps, 1)
mean_ep_reward = np.mean(info["rewards"][-100:])
logger.record_tabular("% completion", completion)
logger.record_tabular("steps", info["steps"])
logger.record_tabular("iters", num_iters)
logger.record_tabular("episodes", len(info["rewards"]))
logger.record_tabular("reward (100 epi mean)",
np.mean(info["rewards"][-100:]))
if not args.noisy:
logger.record_tabular("exploration",
exploration.value(num_iters))
if args.prioritized:
logger.record_tabular("max priority",
replay_buffer._max_priority)
fps_estimate = (float(steps_per_iter) /
(float(iteration_time_est) + 1e-6)
if steps_per_iter._value is not None else
"calculating:")
logger.dump_tabular()
logger.log()
logger.log("ETA: " +
pretty_eta(int(steps_left / fps_estimate)))
logger.log()
# add summary for one episode
ep_stats.add_all_summary(writer, [mean_ep_reward, ep_length],
num_iters)
ep_length = 0
break
if done:
steps_left = args.num_steps - info["steps"]
completion = np.round(info["steps"] / args.num_steps, 1)
mean_ep_reward = np.mean(info["rewards"][-100:])
logger.record_tabular("% completion", completion)
logger.record_tabular("steps", info["steps"])
logger.record_tabular("iters", num_iters)
logger.record_tabular("episodes", len(info["rewards"]))
logger.record_tabular("reward (100 epi mean)",
np.mean(info["rewards"][-100:]))
if not args.noisy:
logger.record_tabular("exploration",
exploration.value(num_iters))
if args.prioritized:
logger.record_tabular("max priority",
replay_buffer._max_priority)
fps_estimate = (
float(steps_per_iter) / (float(iteration_time_est) + 1e-6)
if steps_per_iter._value is not None else "calculating:")
logger.dump_tabular()
logger.log()
logger.log("ETA: " +
pretty_eta(int(steps_left / fps_estimate)))
logger.log()
# add summary for one episode
ep_stats.add_all_summary(writer, [mean_ep_reward, ep_length],
num_iters)
ep_length = 0