run_bc.py [17:34]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def train_agent(env, state_dim, action_dim, max_action, device, output_dir, args):
    # Load buffer
    dataset = d4rl.qlearning_dataset(env)
    data_sampler = Data_Sampler(dataset, device, args.reward_tune)
    utils.print_banner('Loaded buffer')

    if args.algo == 'bc':
        from agents.bc_diffusion import BC as Agent
        agent = Agent(state_dim=state_dim,
                      action_dim=action_dim,
                      max_action=max_action,
                      device=device,
                      discount=args.discount,
                      tau=args.tau,
                      beta_schedule=args.beta_schedule,
                      n_timesteps=args.T,
                      model_type=args.model,
                      lr=args.lr)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



run_offline.py [16:33]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def train_agent(env, state_dim, action_dim, max_action, device, output_dir, args):
    # Load buffer
    dataset = d4rl.qlearning_dataset(env)
    data_sampler = Data_Sampler(dataset, device, args.reward_tune)
    utils.print_banner('Loaded buffer')

    if args.algo == 'bc':
        from agents.bc_diffusion import BC as Agent
        agent = Agent(state_dim=state_dim,
                      action_dim=action_dim,
                      max_action=max_action,
                      device=device,
                      discount=args.discount,
                      tau=args.tau,
                      beta_schedule=args.beta_schedule,
                      n_timesteps=args.T,
                      model_type=args.model,
                      lr=args.lr)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -