--[a]gent (string, required unless "socket-server" remote mode) -- Agent (name, configuration JSON file, or library module)
--[n]etwork (string, default: not specified) -- Network (name, configuration JSON file, or library module)
--[e]nvironment (string, required unless "socket-client" remote mode) -- Environment (name, configuration JSON file, or library module)
--[l]evel (string, default: not specified) -- Level or game id, like CartPole-v1, if supported
--[m]ax-episode-timesteps (int, default: not specified) -- Maximum number of timesteps per episode
--visualize (bool, default: false) -- Visualize agent--environment interaction, if supported
--visualize-directory (bool, default: not specified) -- Directory to store videos of agent--environment interaction, if supported
--import-modules (string, default: not specified) -- Import comma-separated modules required for environment
--num-parallel (int, default: no parallel execution) -- Number of environment instances to execute in parallel
--batch-agent-calls (bool, default: false) -- Batch agent calls for parallel environment execution
--sync-timesteps (bool, default: false) -- Synchronize parallel environment execution on timestep-level
--sync-episodes (bool, default: false) -- Synchronize parallel environment execution on episode-level
--remote (str, default: local execution) -- Communication mode for remote environment execution of parallelized environment execution: "multiprocessing" | "socket-client" | "socket-server". In case of "socket-server", runs environment in server communication loop until closed.
--blocking (bool, default: false) -- Remote environments should be blocking
--host (str, only for "socket-client" remote mode) -- Socket server hostname(s) or IP address(es), single value or comma-separated list
--port (str, only for "socket-client/server" remote mode) -- Socket server port(s), single value or comma-separated list, increasing sequence if single host and port given
--e[v]aluation (bool, default: false) -- Run environment (last if multiple) in evaluation mode
--e[p]isodes (int, default: not specified) -- Number of episodes
--[t]imesteps (int, default: not specified) -- Number of timesteps
--[u]pdates (int, default: not specified) -- Number of agent updates
--mean-horizon (int, default: 1) -- Number of episodes progress bar values and evaluation score are averaged over
--save-best-agent (bool, default: false) -- Directory to save the best version of the agent according to the evaluation score
--[r]epeat (int, default: 1) -- Number of repetitions
--path (string, default: not specified) -- Logging path, directory plus filename without extension
--seaborn (bool, default: false) -- Use seaborn