parser.add_argument("--env", type=str, default="RepeatAfterMeEnv")
parser.add_argument("--num-cpus", type=int, default=0)
parser.add_argument("--framework", choices=["tf", "torch"], default="tf")
parser.add_argument("--as-test", action="store_true")
parser.add_argument("--stop-iters", type=int, default=200)
parser.add_argument("--stop-timesteps", type=int, default=500000)
parser.add_argument("--stop-reward", type=float, default=80)
if __name__ == "__main__":
args = parser.parse_args()
ray.init(num_cpus=args.num_cpus or None)
registry.register_env("RepeatAfterMeEnv", lambda c: RepeatAfterMeEnv(c))
registry.register_env("RepeatInitialObsEnv",
lambda _: RepeatInitialObsEnv())
registry.register_env("LookAndPush", lambda _: OneHot(LookAndPush()))
registry.register_env("StatelessCartPole", lambda _: StatelessCartPole())
config = {
"env": args.env,
# This env_config is only used for the RepeatAfterMeEnv env.
"env_config": {
"repeat_delay": 2,
},
"gamma": 0.99,
# Use GPUs iff `RLLIB_NUM_GPUS` env var set to > 0.
"num_gpus": int(os.environ.get("RLLIB_NUM_GPUS", 0)),
"num_workers": 0,
"num_envs_per_worker": 20,
"entropy_coeff": 0.001,
parser.add_argument("--num-cpus", type=int, default=0)
parser.add_argument("--as-test", action="store_true")
parser.add_argument("--torch", action="store_true")
parser.add_argument("--stop-reward", type=float, default=90)
parser.add_argument("--stop-iters", type=int, default=100)
parser.add_argument("--stop-timesteps", type=int, default=100000)
if __name__ == "__main__":
args = parser.parse_args()
ray.init(num_cpus=args.num_cpus or None)
ModelCatalog.register_custom_model(
"rnn", TorchRNNModel if args.torch else RNNModel)
register_env("RepeatAfterMeEnv", lambda c: RepeatAfterMeEnv(c))
register_env("RepeatInitialObsEnv", lambda _: RepeatInitialObsEnv())
config = {
"env": args.env,
"env_config": {
"repeat_delay": 2,
},
"gamma": 0.9,
# Use GPUs iff `RLLIB_NUM_GPUS` env var set to > 0.
"num_gpus": int(os.environ.get("RLLIB_NUM_GPUS", "0")),
"num_workers": 0,
"num_envs_per_worker": 20,
"entropy_coeff": 0.001,
"num_sgd_iter": 5,
"vf_loss_coeff": 1e-5,
"model": {
torch.unsqueeze(state[1], 0)])
action_out = self.action_branch(lstm_out[0])
self._cur_value = torch.reshape(self.value_branch(lstm_out[0]), [-1])
return action_out, [
torch.squeeze(lstm_out[1][0], 0),
torch.squeeze(lstm_out[1][1], 0)
]
if __name__ == "__main__":
args = parser.parse_args()
ray.init(num_cpus=args.num_cpus or None)
ModelCatalog.register_custom_model("rnn", RNNModel)
tune.register_env("repeat_initial",
lambda _: RepeatInitialObsEnv(episode_len=100))
tune.register_env("repeat_after_me",
lambda _: RepeatAfterMeEnv({"repeat_delay": 1}))
tune.register_env("stateless_cartpole", lambda _: StatelessCartPole())
config = {
"env": args.env,
"use_pytorch": True,
"num_workers": 0,
"num_envs_per_worker": 20,
"gamma": 0.9,
"entropy_coeff": 0.0001,
"model": {
"custom_model": "rnn",
"max_seq_len": 20,
"lstm_use_prev_action_reward": "store_true",
