CUP Brings GAE into Safe Policy Updates, Hitting 2025 Return on Hopper Under the Cost Cap

Constrained Update Projection Approach to Safe Policy Optimization

Long Yang, Jiaming Ji, Juntao Dai, Linrui Zhang, Binbin Zhou, Pengfei Li, Yaodong Yang, Gang Pan

cs.LG, cs.AI

2022-09-15

CUP improves a GAE surrogate then projects back onto the safe set with first-order updates: Hopper return 2025 vs FOCOPS 1688, with cost 79.98 under the cap of 83.

What problem this solves

Safe RL in a CMDP must raise return while keeping cost return under a budget. CPO and PCPO replace the objective and constraints with surrogates, then convexify a nonconvex problem with first- or second-order Taylor steps, and invert a high-dimensional Fisher matrix on every update. That is expensive and biased in high-dimensional control. Lagrangian methods run, but intermediate policies often already violate the constraint and cannot be executed on hardware.

Theory has a hole too. GAE is the default variance-reduction tool, and some CPO-style code already plugs it in, without a performance bound that actually contains GAE. CUP supplies that bound and a first-order implementation that skips convexity approximations.

Method

The paper proves a generalized performance-difference bound between any two policies, with error terms from both TD residuals and discounted occupancy mismatch. With p=1, q=∞ the bound is written in GAE advantages; as λ→0 it recovers CPO's classical bound. The cost functional has a matching upper bound. TV distance can be replaced by the square root of KL for a trust-region penalty.

The algorithm has two steps. Step one maximizes an importance-sampled GAE advantage on data from the old policy, minus a KL-root penalty, producing a temporary policy that may be unsafe. Step two projects that policy back: minimize distance to the temporary policy subject to a GAE cost upper bound plus a KL-root penalty staying under budget b. Theorem 2 bounds worst-case return drop and constraint violation; safety is asymptotic as α and β go to 0.

The implementation never convexifies. The projection is a primal-dual problem in a multiplier ν; both the policy and ν take first-order steps, with ν clipped at 0. All estimates come from on-policy samples, and the cost advantage is GAE as well.

Results

MuJoCo runs use 10 seeds, Safety Gym 3, against CPO, PCPO, TRPO-L, PPO-L, and FOCOPS. CUP's cost traces hug the limit line in most environments; baselines overshoot or under-correct. On Ant-v3 only FOCOPS and CUP stay safe, and CUP's return is higher. On Swimmer-v3 PPO-L's return 35.58 beats CUP's 33.38, but its cost is 54.91 against a limit of 24.5, a dangerous policy. On Safety Gym, CPO/PCPO start infeasible on PointGoal and PointButton.

EnvLimitCUP returnCUP costBest baseline return (feasibility)
Ant-v31031743.66±40.599.11±0.93FOCOPS 1662.53 (cost 101.31, on the line)
Hopper-v3832025.56±122.3579.98±2.31FOCOPS 1687.72 (cost 102.3, violation)
Swimmer-v324.533.38±0.5423.31±0.05PPO-L 35.58 (cost 54.91, violation)
Humanoid-v3201066.83±266.1219.91±0.36PCPO 962.13 (cost 48.66, violation)
Humanoid-Circle50768.65±63.7048.23±0.65FOCOPS 713.04 (cost 47.73, safe)

When estimated cost sits under the budget, ν stays quiet; once it crosses, ν activates and pulls the policy back. Return and cost stay stable across a range of α. Changing the limit, CUP still tracks the new b.

Why it matters

This puts GAE inside a safety bound and ships it with first-order updates, without a Fisher inverse on every step. For a continuous-control stack that already runs PPO/GAE, the projection step is an extra safety layer rather than a new second-order solver. On the numbers, the gain is mostly "others violate, this one hugs the cap", not a new return ceiling in every env. On Swimmer, CUP returns less than a violating PPO-L. That is the trade a safe algorithm is supposed to make.

Limitations

The authors tick "no" on a dedicated limitations section. Theorem 2's safety is approximate, with remainders that depend on KL and cost-estimation error; α and β must go to 0 for the asymptotic claim, so finite-step runs can still graze the cap. Humanoid-v3 return has a 266 standard deviation across seeds. Safety Gym uses three seeds. The paper does not itemize whether every baseline used its authors' official hyperparameters. Experiments are single-cost; multiple constraints, misspecified cost functions, and real robots are out of scope. The projection estimates the constraint from on-policy samples, so a biased cost estimator biases the guarantee.

Terms

Source

What people are saying

Related papers

All paper explainers